© 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. 72584
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    你也
    -1.73
    鲠
    -1.63
     используя
    -1.55
     echter
    -1.54
     ogrom
    -1.51
     You
    -1.46
    愎
    -1.45
    udière
    -1.45
     ekip
    -1.43
    を追
    -1.42
    POSITIVE LOGITS
    躋
    1.96
     його
    1.83
    ྥ
    1.78
    Despite
    1.67
     Morro
    1.66
    珦
    1.66
    巿
    1.64
     '';
    1.63
    Also
    1.61
    Typically
    1.61
    Activations Density 0.028%

    No Known Activations