© 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. 125422
    Prev
    Next
    INDEX
    Explanations

    offering, to, fun, rather, tote

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

    patterns of "repeatedly try"

    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
    dic
    0.47
    puesta
    0.46
     subjects
    0.45
     '\
    0.45
     subj
    0.44
    bajo
    0.44
    ['
    0.44
    el
    0.44
     ff
    0.43
     won
    0.43
    POSITIVE LOGITS
    📸
    0.50
    债券
    0.49
     BOND
    0.47
     TREATMENT
    0.46
     SERVICE
    0.46
    ⺝
    0.46
     STUDY
    0.46
    臨床
    0.45
    😋
    0.45
    修行
    0.45
    Activations Density 0.000%

    No Known Activations