© 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. 130914
    Prev
    Next
    INDEX
    Explanations

    titles or specific phrases

    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
     its
    -1.07
     for
    -1.01
     with
    -1.00
    先は
    -0.97
     get
    -0.94
     each
    -0.93
     без
    -0.91
    lakukan
    -0.88
     which
    -0.88
     bicicleta
    -0.87
    POSITIVE LOGITS
    asure
    1.05
     consente
    1.04
     alimentare
    1.02
     manteiga
    0.96
    たっぷり
    0.95
     твое
    0.95
     elettrico
    0.93
    msub
    0.93
     университе
    0.93
     kaufen
    0.92
    Activations Density 0.000%

    No Known Activations