© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84684
    Prev
    Next
    INDEX
    Explanations

    casting spells

    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
    alnız
    -0.74
    Aç
    -0.73
    physiological
    -0.73
     Crocker
    -0.73
     Año
    -0.71
    quirer
    -0.71
     firearms
    -0.71
     encar
    -0.70
     organización
    -0.69
    вете
    -0.69
    POSITIVE LOGITS
     casting
    3.23
     cast
    3.16
    casting
    2.81
     Casting
    2.72
    Casting
    2.64
    Cast
    2.53
    cast
    2.42
     CAST
    2.41
     Cast
    2.38
     casts
    2.38
    Activations Density 0.014%

    No Known Activations