© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108545
    Prev
    Next
    INDEX
    Explanations

    determination of recovery

    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
    ventajas
    -0.72
    叨
    -0.72
    ngrx
    -0.69
    很赞
    -0.69
    灵活
    -0.68
     Mä
    -0.68
    かす
    -0.68
    签订
    -0.66
    estrutura
    -0.66
    ([]);
    -0.66
    POSITIVE LOGITS
     recovery
    1.99
    Recovery
    1.87
     Recovery
    1.87
     recoveries
    1.85
    recovery
    1.69
     Recover
    1.50
    Recover
    1.49
     RECOVERY
    1.49
     recovers
    1.37
    recover
    1.35
    Activations Density 0.015%

    No Known Activations