© 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. 201393
    Prev
    Next
    INDEX
    Explanations

    monthly choices of coupon codes

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

    but as

    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
    定
    0.48
    沙漠
    0.46
    形势
    0.45
     clandestine
    0.45
    0.45
    デス
    0.45
     निय
    0.44
    を起こ
    0.43
    しくは
    0.43
     handleSubmit
    0.43
    POSITIVE LOGITS
    MA
    0.56
    MI
    0.55
    K
    0.54
    oh
    0.53
    als
    0.52
    GY
    0.52
    GE
    0.51
    arm
    0.50
    TP
    0.50
    ADA
    0.50
    Activations Density 0.000%

    No Known Activations