© 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. 225065
    Prev
    Next
    INDEX
    Explanations

    Upon stealing

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

    asking about liking this

    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
     p
    0.49
     AND
    0.47
    ium
    0.45
     wrote
    0.44
     片
    0.44
     网络
    0.43
     usr
    0.42
     п
    0.42
    io
    0.42
    heds
    0.41
    POSITIVE LOGITS
    ዢ
    0.44
     kinerja
    0.43
    效
    0.42
     erneut
    0.41
    permissionid
    0.41
    րա
    0.40
     diagonals
    0.40
    enang
    0.40
    ляции
    0.39
    MNumber
    0.39
    Activations Density 0.000%

    No Known Activations