© 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. 71671
    Prev
    Next
    INDEX
    Explanations

    drawer, squirrel

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

    The neuron fires on occurrences of the word “drawer” (in any context or capitalization).

    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
     was
    -3.17
    $
    -2.95
    敉
    -2.42
     \
    -2.30
    "
    -2.30
    这里
    -2.19
     alimente
    -2.17
     didn
    -2.17
    垰
    -2.16
     say
    -2.14
    POSITIVE LOGITS
    <bos>
    2.88
    ፨
    2.53
    灕
    2.45
    ꒥
    2.44
     mencegah
    2.42
    Ꮏ
    2.42
    虓
    2.42
     kosong
    2.33
     çocuklar
    2.30
    外的
    2.25
    Activations Density 0.002%

    No Known Activations