© 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. 22269
    Prev
    Next
    INDEX
    Explanations

    sz

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

    The neuron never activates on any token—it’s effectively “dead” and doesn’t detect any pattern.

    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
    
    -2.91
    阇
    -2.78
    ญี่ป
    -2.64
    喈
    -2.58
    鋮
    -2.52
    昻
    -2.45
    唞
    -2.45
    侭
    -2.42
    ⽌
    -2.42
     शुर
    -2.38
    POSITIVE LOGITS
    \
    3.73
    s
    3.20
    _
    3.13
    <
    3.11
    ",
    3.03
    *
    2.92
    —
    2.86
    "—
    2.75
    [
    2.70
    },
    2.63
    Activations Density 0.002%

    No Known Activations