© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11316
    Prev
    Next
    INDEX
    Explanations

    locations after at

    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
     this
    -1.79
    What
    -1.56
    Some
    -1.41
    Two
    -1.41
    Only
    -1.36
    According
    -1.36
    および
    -1.33
    Along
    -1.30
    できるだけ
    -1.30
    what
    -1.29
    POSITIVE LOGITS
     kolem
    1.37
    </em>
    1.32
     corrientes
    1.26
     skvě
    1.26
    veloppe
    1.23
     čier
    1.21
    velse
    1.20
     např
    1.20
    ULES
    1.20
     NSCoder
    1.17
    Activations Density 0.001%

    No Known Activations