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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25913
    Prev
    Next
    INDEX
    Explanations

    void function definitions

    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_34/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
     pública
    -0.78
     público
    -0.76
    StartIndex
    -0.74
    Срок
    -0.72
     tacit
    -0.72
    味噌
    -0.72
    ׳
    -0.70
    醤油
    -0.69
    Fordítás
    -0.68
    (´
    -0.68
    POSITIVE LOGITS
    achelor
    0.93
    }|
    0.91
     Initialize
    0.90
    ⎨
    0.86
    USTER
    0.83
    },[])
    0.82
    xbb
    0.81
    )}]{
    0.81
    altra
    0.80
    triangle
    0.80
    Activations Density 0.001%

    No Known Activations