© 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. 105920
    Prev
    Next
    INDEX
    Explanations

    mosaic inlay

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

    brain reset

    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
    يري
    0.51
    镟
    0.49
    _{-}\
    0.49
    喡
    0.47
     energético
    0.47
    postId
    0.47
     ചെറിയ
    0.46
    лик
    0.46
    㭂
    0.45
    рий
    0.45
    POSITIVE LOGITS
     pointwise
    0.48
    :
    0.46
    (
    0.46
     wyłącznie
    0.43
    স্ত
    0.42
     mieszkań
    0.42
    一些
    0.40
    getto
    0.40
    stan
    0.40
     đột
    0.40
    Activations Density 0.001%

    No Known Activations