© 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. 1809
    Prev
    Next
    INDEX
    Explanations

    music concerts, scientific culture, convention center

    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
    Articolo
    -1.55
     noastră
    -1.40
    ateľ
    -1.37
     školy
    -1.37
    ecturer
    -1.34
     restricting
    -1.33
    ťaž
    -1.33
     škola
    -1.31
    Quali
    -1.30
     tradizionale
    -1.30
    POSITIVE LOGITS
    from
    1.66
    1.49
    çou
    1.41
    BLK
    1.40
     '-':
    1.38
    鲧
    1.36
     Februari
    1.34
    lización
    1.33
    have
    1.30
    isait
    1.30
    Activations Density 0.152%

    No Known Activations