© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101580
    Prev
    Next
    INDEX
    Explanations

    horizontal rules and dividers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    {
    -2.44
    ta
    -2.19
    ar
    -2.16
    <bos>
    -2.06
    The
    -1.95
    www
    -1.95
    ha
    -1.93
    1
    -1.93
    *
    -1.91
    T
    -1.89
    POSITIVE LOGITS
    }$,
    2.33
    }=
    2.05
     of
    2.00
    ógicos
    1.98
     in
    1.98
     —
    1.94
    selbe
    1.91
    皛
    1.85
    ;%%
    1.84
     köy
    1.83
    Activations Density 0.006%

    No Known Activations