© 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. 61206
    Prev
    Next
    INDEX
    Explanations

    going home

    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
     другими
    -2.00
    _
    -1.84
    .
    -1.76
     you
    -1.75
     molto
    -1.70
     {
    -1.69
     хотите
    -1.66
    ("
    -1.63
     :
    -1.63
    </strong>
    -1.63
    POSITIVE LOGITS
     anún
    2.09
    tivation
    1.98
    ritation
    1.97
    sery
    1.96
    ictions
    1.95
    positivos
    1.95
    spectos
    1.91
    ñadir
    1.88
    cellent
    1.83
    дания
    1.82
    Activations Density 0.005%

    No Known Activations