© 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. 10-GEMMASCOPE-RES-131K
    7. 127846
    Prev
    Next
    INDEX
    Explanations

    just fine

    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_10/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
     of
    -2.59
     anderen
    -1.91
     剧照
    -1.68
    coins
    -1.60
    龗
    -1.59
    regierung
    -1.57
     informé
    -1.57
     karena
    -1.55
    vať
    -1.54
    banks
    -1.54
    POSITIVE LOGITS
     used
    1.73
    =
    1.62
    )
    1.61
    选举
    1.54
     described
    1.50
     usado
    1.49
    前から
    1.48
     utilizado
    1.48
     probably
    1.41
     *
    1.38
    Activations Density 0.013%

    No Known Activations