© 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. 10051
    Prev
    Next
    INDEX
    Explanations

    Relationship Manager

    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
    ↵
    0.57
    ↵↵
    0.55
     “
    0.54
     the
    0.53
     The
    0.48
    the
    0.47
    /
    0.47
     A
    0.45
     more
    0.44
     "
    0.44
    POSITIVE LOGITS
    <unused85>
    0.40
    avacanam
    0.40
    apayati
    0.39
    <start_of_turn>
    0.39
    <unused55>
    0.38
    躹
    0.38
    <unused54>
    0.38
    󰀄
    0.38
    <unused23>
    0.37
    <unused25>
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.