© 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. 89553
    Prev
    Next
    INDEX
    Explanations

    code imports from modules

    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
    1
    0.58
    (
    0.55
    0
    0.55
    7
    0.52
    、
    0.52
    \
    0.51
    （
    0.49
    9
    0.48
    5
    0.48
    4
    0.48
    POSITIVE LOGITS
    asida
    0.43
     ば
    0.43
     විශේෂ
    0.40
     sva
    0.40
     특집
    0.40
     Uma
    0.39
     पहिला
    0.39
     ఆమె
    0.38
    逖
    0.38
     ടീ
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.