© 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. 41477
    Prev
    Next
    INDEX
    Explanations

    future, for, and, that

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

    sequences, availability, impact

    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
    s
    0.69
    y
    0.57
    1
    0.54
    en
    0.52
    m
    0.51
     trace
    0.50
     Trace
    0.50
    at
    0.49
    recycl
    0.49
    formatter
    0.49
    POSITIVE LOGITS
     칼
    0.54
     calves
    0.53
     ಕರಿ
    0.53
     কলিক
    0.52
     adhipp
    0.51
     ಸಂಖ್ಯ
    0.50
    lockSeconds
    0.50
    fqsen
    0.50
     例えば
    0.50
    칼
    0.50
    Activations Density 0.000%

    No Known Activations