© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57088
    Prev
    Next
    INDEX
    Explanations

    hard work blowouts

    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
    읍
    -0.90
     Tower
    -0.73
     Towers
    -0.72
    riko
    -0.70
     OV
    -0.69
     imperf
    -0.69
    といけない
    -0.69
    Tower
    -0.69
     tower
    -0.69
     Soccerway
    -0.67
    POSITIVE LOGITS
    utada
    0.71
     keç
    0.70
    outs
    0.70
     fisik
    0.69
    getter
    0.68
     tưởng
    0.68
     viime
    0.68
     podjet
    0.67
     fian
    0.67
     !}
    0.66
    Activations Density 0.021%

    No Known Activations