© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85445
    Prev
    Next
    INDEX
    Explanations

    aphid or ATF

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

    abbreviations and acronyms like ATF, AFT, and references to aphids.

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

    The neuron fires strongly on the word “aphid” (and related taxonomic forms), so it is detecting mentions of aphids.

    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
     sparkly
    -2.53
     edgy
    -2.31
    momile
    -2.13
     flawless
    -2.09
     prioriti
    -2.06
    ꙳
    -2.05
     cocky
    -2.00
     seductive
    -1.99
     roky
    -1.98
    饗
    -1.96
    POSITIVE LOGITS
    r
    2.86
    u
    2.70
    “
    2.64
    c
    2.20
    2
    2.13
    to
    2.11
    x
    2.05
    k
    2.03
     conspicuously
    1.97
    ↵↵
    1.93
    Activations Density 0.004%

    No Known Activations