© 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. 22-GEMMASCOPE-RES-131K
    4. 70511
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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_22/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
     of
    -1.77
     but
    -1.65
     not
    -1.46
     again
    -1.23
     to
    -1.20
     and
    -1.18
     or
    -1.15
     since
    -1.14
     because
    -1.13
     although
    -1.13
    POSITIVE LOGITS
     légitime
    1.16
     sellado
    1.15
     refroid
    1.14
     Mereka
    1.13
     coû
    1.13
     réjou
    1.13
     repuesto
    1.12
    itets
    1.12
    especial
    1.09
    Noch
    1.08
    Activations Density 0.057%

    No Known Activations