© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113047
    Prev
    Next
    INDEX
    Explanations

    solving problems

    np_acts-logits-general · gemini-2.5-flash-lite

    medical receipts summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.49
    Decrypt
    0.49
    ūsų
    0.48
    Murder
    0.48
    en
    0.48
    د
    0.47
    ilet
    0.47
     приводит
    0.47
    aş
    0.47
    م
    0.47
    POSITIVE LOGITS
     predominant
    0.53
     line
    0.53
     blossom
    0.53
     computation
    0.51
     lowland
    0.49
     numerical
    0.49
     youngest
    0.49
     Zoll
    0.49
    颐
    0.48
     anomaly
    0.48
    Activations Density 0.000%

    No Known Activations