© 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. 38526
    Prev
    Next
    INDEX
    Explanations

    XML tags or versioning

    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
     inhal
    -0.79
    พูด
    -0.75
     transformación
    -0.73
     drafts
    -0.71
    ұ
    -0.70
     counseling
    -0.69
    haling
    -0.68
     Modeling
    -0.68
     inhale
    -0.68
    Modeling
    -0.68
    POSITIVE LOGITS
    pam
    0.82
    эле
    0.73
     pam
    0.69
    思議
    0.67
    嗗
    0.66
    euro
    0.65
     Absence
    0.64
     НЕ
    0.63
    мета
    0.63
     Pam
    0.62
    Activations Density 0.067%

    No Known Activations