© 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. 76116
    Prev
    Next
    INDEX
    Explanations

    words starting with Cla-

    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
    ishin
    -0.82
    ientôt
    -0.80
     Igual
    -0.79
    ocardium
    -0.78
    onymes
    -0.78
    쉐
    -0.77
    렀
    -0.77
     ciclismo
    -0.76
    inici
    -0.76
    sprache
    -0.75
    POSITIVE LOGITS
     cla
    1.74
     Cla
    1.63
    cla
    1.59
    Cla
    1.56
     Clau
    1.26
     kla
    0.96
     clap
    0.96
     Kla
    0.93
     CLA
    0.92
     claw
    0.92
    Activations Density 0.031%

    No Known Activations