© 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. 22-GEMMASCOPE-RES-131K
    7. 27675
    Prev
    Next
    INDEX
    Explanations

    sufficiency and thresholds

    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_22/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
    いつも
    -1.02
    noStroke
    -0.97
    Always
    -0.91
    ﾐ
    -0.91
     "",
    -0.90
    Nachdem
    -0.89
    Пи
    -0.84
    Each
    -0.82
    Укра
    -0.82
    Informationen
    -0.82
    POSITIVE LOGITS
    sufficient
    1.22
     suffisamment
    1.19
     cualquier
    1.12
     sufficiently
    1.10
     suficientemente
    1.08
     geeignet
    1.04
     Sufficient
    1.02
    場所に
    1.01
    alipay
    1.01
     combination
    1.01
    Activations Density 0.057%

    No Known Activations