© 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. 117374
    Prev
    Next
    INDEX
    Explanations

    song titles and quotes

    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
    嘻嘻
    -0.87
    technologies
    -0.85
    శ
    -0.84
    ឿ
    -0.84
    }+$
    -0.84
    ⿳
    -0.84
     pás
    -0.84
     Otros
    -0.83
    kue
    -0.82
     lás
    -0.81
    POSITIVE LOGITS
    拱
    0.75
     Get
    0.73
    鏖
    0.73
     посту
    0.73
    uramente
    0.73
    rit
    0.71
     bước
    0.71
     bite
    0.69
    циали
    0.69
     taint
    0.68
    Activations Density 0.027%

    No Known Activations