© 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. 86736
    Prev
    Next
    INDEX
    Explanations

    tips for success

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

    basic checks

    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
    수
    0.59
    ሬ
    0.49
    Cx
    0.47
    жи
    0.46
    제
    0.46
    름
    0.46
    OF
    0.45
    产业链
    0.45
    context
    0.45
    죵
    0.45
    POSITIVE LOGITS
    ாவும்
    0.53
     ஏதாவது
    0.49
     automatisch
    0.49
     sondern
    0.49
     accompany
    0.47
     avrebbe
    0.47
     über
    0.47
    illes
    0.47
     estavam
    0.47
     overlooking
    0.46
    Activations Density 0.001%

    No Known Activations