© 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. 41748
    Prev
    Next
    INDEX
    Explanations

    previously reported or described

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

    availability and price

    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
     перегово
    0.59
    关系的
    0.53
     синд
    0.50
     уены
    0.50
    리와
    0.49
     인사
    0.49
    总经理
    0.47
    멘
    0.47
    走进
    0.47
     уйнау
    0.47
    POSITIVE LOGITS
     expensive
    0.59
     pricey
    0.57
     (>
    0.52
     op
    0.50
     available
    0.50
     obtainable
    0.49
     Expensive
    0.49
     cheap
    0.48
     elastomer
    0.48
     inexpensive
    0.48
    Activations Density 0.000%

    No Known Activations