© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    opening of phrases or code

    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
     that
    -1.71
     this
    -1.36
     those
    -1.13
     in
    -0.95
    weihnachts
    -0.94
    That
    -0.91
     there
    -0.91
     their
    -0.90
    tifiable
    -0.85
    ństw
    -0.85
    POSITIVE LOGITS
    出了
    1.01
     Horticulture
    0.95
     yes
    0.95
     smallest
    0.94
    OutputPath
    0.93
     soooo
    0.91
     sooo
    0.90
     изготов
    0.89
     横浜
    0.89
    tól
    0.88
    Activations Density 0.000%

    No Known Activations