© 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. 11487
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     on
    -1.33
     using
    -1.32
     one
    -1.26
     from
    -1.20
     will
    -1.20
     with
    -1.17
     inimes
    -1.16
     before
    -1.15
     gives
    -1.14
     kõik
    -1.12
    POSITIVE LOGITS
     diversos
    1.29
     diverses
    1.14
     pn
    1.14
    swept
    1.12
     alcuni
    1.12
     dette
    1.10
    などが
    1.08
     tumultuous
    1.07
     рассматри
    1.05
    urés
    1.04
    Activations Density 0.006%

    No Known Activations