© 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. 10-GEMMASCOPE-RES-131K
    4. 509
    Prev
    Next
    INDEX
    Explanations

    actions and capabilities

    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
     as
    -2.88
     also
    -2.53
     in
    -2.30
     with
    -2.08
     or
    -1.93
     putting
    -1.92
    ૪
    -1.80
     taking
    -1.78
     for
    -1.75
     all
    -1.73
    POSITIVE LOGITS
    齮
    2.02
     verschied
    1.87
     célè
    1.85
     ไม่มี
    1.83
    BOTH
    1.80
    Therefore
    1.74
     bascul
    1.72
     refroid
    1.64
     rafraî
    1.64
     ältere
    1.63
    Activations Density 0.027%

    No Known Activations