© 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. 72814
    Prev
    Next
    INDEX
    Explanations

    Mack names

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

    The neuron is a “rare‐token detector” that lights up strongly on unusual or specialized words (often proper names or technical terms).

    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
    vantaged
    -2.75
     If
    -2.55
    本章
    -2.42
    咔嚓
    -2.42
    接下来的
    -2.39
     It
    -2.39
    </sub>
    -2.38
    følgelig
    -2.38
    伱
    -2.33
    瓩
    -2.30
    POSITIVE LOGITS
    z
    3.61
    p
    3.42
    i
    3.22
    x
    2.97
    那我
    2.94
    n
    2.84
    k
    2.78
    f
    2.66
    ﮕ
    2.61
    ).
    2.56
    Activations Density 0.028%

    No Known Activations