© 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. 29353
    Prev
    Next
    INDEX
    Explanations

    PMCID numbers

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

    numbers in url paths

    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
    )^{-\
    0.40
    RESS
    0.40
    ^{*}(\
    0.40
    UTICAL
    0.39
    ROSS
    0.38
    姓
    0.38
    HEN
    0.38
     firmer
    0.37
    ESTER
    0.37
    )^{[\
    0.36
    POSITIVE LOGITS
    4
    0.73
    9
    0.68
    6
    0.66
    7
    0.66
    3
    0.63
    8
    0.63
    2
    0.60
    5
    0.59
    1
    0.57
     ১৩
    0.48
    Activations Density 0.017%

    No Known Activations