© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100919
    Prev
    Next
    INDEX
    Explanations

    archaea and archaic

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

    words related to archaea or archaeal organisms, particularly in scientific contexts.

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

    The neuron is tuned to pick up references to the archaeal domain, activating on “archae,” “archaeal,” “archaeon,” and similar forms.

    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
    籴
    -2.19
    ⩴
    -2.19
    鹩
    -2.14
    泐
    -2.13
    蕺
    -2.06
    謳
    -1.96
    鬈
    -1.94
    旆
    -1.93
    を知
    -1.88
    鹇
    -1.88
    POSITIVE LOGITS
     —
    2.36
    琑
    2.09
    S
    2.08
     \
    2.05
    in
    1.95
    at
    1.88
    '
    1.82
    嚳
    1.81
    x
    1.75
    难以
    1.70
    Activations Density 0.016%

    No Known Activations