© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12348
    Prev
    Next
    INDEX
    Explanations

    social commentary on social issues

    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
     for
    -1.90
     with
    -1.85
     of
    -1.84
     will
    -1.64
     from
    -1.44
     at
    -1.41
     in
    -1.40
     still
    -1.31
     time
    -1.31
     his
    -1.30
    POSITIVE LOGITS
     höl
    1.66
     dekol
    1.60
    fotograf
    1.60
     heilige
    1.52
    plakat
    1.51
    kalender
    1.50
     treff
    1.49
     kanad
    1.46
     kollek
    1.45
     konkret
    1.43
    Activations Density 0.056%

    No Known Activations