© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100006
    Prev
    Next
    INDEX
    Explanations

    saline solutions or waters

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to salt content or salinity in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on occurrences of “salinity” (and related “saline”)—especially when paired with quantitative values—i.e. sections reporting salinity measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -3.16
    iocene
    -2.45
    ederos
    -2.27
    黉
    -2.22
     However
    -2.19
    橼
    -2.16
    medriver
    -2.14
     Whether
    -2.13
     We
    -2.06
    aimeJ
    -2.06
    POSITIVE LOGITS
    e
    3.09
    i
    3.00
    -
    2.20
    D
    2.03
    ists
    1.99
    C
    1.98
    1
    1.92
    い
    1.91
    ЛОВ
    1.82
     parado
    1.80
    Activations Density 0.004%

    No Known Activations