© 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. 45371
    Prev
    Next
    INDEX
    Explanations

    CG, CF, MD types

    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
    ⓝ
    -0.75
    Географија
    -0.73
    正义
    -0.70
    Wayne
    -0.69
    UVWXYZ
    -0.68
    Eld
    -0.68
    Chalk
    -0.68
    ELD
    -0.68
     Belk
    -0.67
    ()['
    -0.67
    POSITIVE LOGITS
     CF
    1.38
    CF
    1.32
     CFD
    1.02
    cf
    0.90
     کر
    0.89
     cf
    0.89
     Cf
    0.89
     Ref
    0.87
    reau
    0.83
    Ref
    0.81
    Activations Density 0.082%

    No Known Activations