© 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. 31350
    Prev
    Next
    INDEX
    Explanations

    code and language identifiers

    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
     diskusi
    -0.93
     définiti
    -0.86
     deportivas
    -0.83
     geheim
    -0.81
     edificio
    -0.80
    อ่าน
    -0.80
    ákat
    -0.80
     détaillés
    -0.79
    goti
    -0.78
     čier
    -0.78
    POSITIVE LOGITS
     prés
    0.90
     Dill
    0.85
     teil
    0.84
    这不
    0.84
     通販
    0.83
     speci
    0.82
    経過
    0.82
    いくら
    0.80
     mistaken
    0.79
    どれだけ
    0.79
    Activations Density 0.028%

    No Known Activations