© 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. 121251
    Prev
    Next
    INDEX
    Explanations

    #1 goal, #5 continues

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

    task planning and information stages

    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
    ot
    0.53
    ol
    0.49
    ТА
    0.47
    or
    0.46
    ay
    0.46
    水印
    0.46
    a
    0.45
    ه
    0.45
    eld
    0.44
     Citadel
    0.44
    POSITIVE LOGITS
     일반
    0.49
     이야기
    0.47
    ເລັກ
    0.47
    ributor
    0.47
     어린
    0.47
     యువ
    0.45
     이야기를
    0.45
     incredible
    0.45
     immensely
    0.45
    ിലേ
    0.44
    Activations Density 0.000%

    No Known Activations