© 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. 103591
    Prev
    Next
    INDEX
    Explanations

    patterns following specific tokens

    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
     Trenton
    -0.82
    MANUEL
    -0.81
    Kara
    -0.76
    Rw
    -0.76
    butt
    -0.75
     Romero
    -0.75
     ð
    -0.74
     Kara
    -0.73
    řez
    -0.73
     Mixture
    -0.71
    POSITIVE LOGITS
     enco
    0.82
    endl
    0.77
     beaming
    0.75
     Psychologie
    0.75
    bahasan
    0.74
    Drilling
    0.73
     Sich
    0.73
     Tuba
    0.73
     subray
    0.73
     návště
    0.73
    Activations Density 0.011%

    No Known Activations