© 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. 77626
    Prev
    Next
    INDEX
    Explanations

    versions and numbers

    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
    lv
    0.47
    lu
    0.43
    lje
    0.42
    %%%
    0.40
    loggedin
    0.40
    hörigen
    0.40
    cS
    0.39
    lai
    0.39
    ladi
    0.39
    _
    0.39
    POSITIVE LOGITS
     Hispan
    0.41
     आयुष्मान
    0.41
     Corpor
    0.40
     Unicode
    0.40
     Resize
    0.40
     Serialization
    0.40
    一張
    0.40
     новий
    0.39
     جديد
    0.39
     Blick
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.