© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40998
    Prev
    Next
    INDEX
    Explanations

    from images

    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
    {
    -1.88
     who
    -1.74
     retira
    -1.68
     any
    -1.66
    ),
    -1.66
     what
    -1.66
     anybody
    -1.59
    _
    -1.56
     fortale
    -1.54
     you
    -1.52
    POSITIVE LOGITS
     الساعة
    1.42
    uxxxx
    1.38
     poète
    1.30
    ⚾
    1.29
     écout
    1.23
    oluted
    1.23
    🎾
    1.23
     and
    1.20
    Ⅲ
    1.18
    zwischen
    1.17
    Activations Density 0.001%

    No Known Activations