© 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. 69518
    Prev
    Next
    INDEX
    Explanations

    can activate

    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
     from
    -1.89
     its
    -1.61
     of
    -1.52
     However
    -1.50
     But
    -1.46
    These
    -1.38
     Until
    -1.35
    r
    -1.33
     with
    -1.30
     them
    -1.29
    POSITIVE LOGITS
     phénom
    1.44
     menyen
    1.41
     FÜR
    1.41
     funktion
    1.39
    tront
    1.37
    dicos
    1.35
     harán
    1.35
    獬
    1.34
     tersenyum
    1.33
    canActivate
    1.31
    Activations Density 0.310%

    No Known Activations