© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99611
    Prev
    Next
    INDEX
    Explanations

    besides, introduce additional points

    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
     also
    -1.87
    </i>
    -1.83
     eigentliche
    -1.82
    4
    -1.78
     were
    -1.77
    }\
    -1.67
     owing
    -1.66
     concerning
    -1.65
     также
    -1.64
    ka
    -1.59
    POSITIVE LOGITS
    which
    1.91
     แล้ว
    1.77
    стреча
    1.73
    镡
    1.71
    COMES
    1.68
    <0x00>
    1.66
    Luego
    1.65
     Après
    1.63
    that
    1.63
    eafter
    1.63
    Activations Density 0.004%

    No Known Activations