© 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. 57576
    Prev
    Next
    INDEX
    Explanations

    Kurt Cobain and Nirvana

    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
     vervol
    -0.83
    Mafia
    -0.82
    訌
    -0.80
     Pfeffer
    -0.79
    صة
    -0.79
    tensorflow
    -0.71
    ://"
    -0.69
    ibouti
    -0.68
    мога
    -0.67
    क्टर
    -0.67
    POSITIVE LOGITS
     Nirvana
    2.06
     Kurt
    1.60
    Nirvana
    1.55
     Cob
    1.38
    Kurt
    1.34
     grunge
    1.34
    Cob
    1.30
     Seattle
    1.29
    NIR
    1.20
     nirvana
    1.19
    Activations Density 0.038%

    No Known Activations