© 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. 90503
    Prev
    Next
    INDEX
    Explanations

    cast, caste, caster

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of the character sequence “cast” (in any case) within a token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     席
    -0.77
     blick
    -0.74
     Remembering
    -0.73
    ränken
    -0.73
     kelime
    -0.73
    authorization
    -0.72
     μπ
    -0.71
     attract
    -0.71
    derive
    -0.69
     verlo
    -0.69
    POSITIVE LOGITS
     Cast
    0.95
     cast
    0.91
    Cast
    0.82
     caste
    0.81
     Bayer
    0.78
     caster
    0.78
     castor
    0.76
     EdgeInsets
    0.75
     Troy
    0.75
    кожа
    0.71
    Activations Density 0.011%

    No Known Activations