© 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. 49957
    Prev
    Next
    INDEX
    Explanations

    database, prism, prediction, performance, belief

    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
    _
    0.55
    配色
    0.47
    -
    0.44
     Includes
    0.42
     شامل
    0.42
    有关
    0.41
     Div
    0.40
    نگی
    0.40
    ♻
    0.40
    来看
    0.39
    POSITIVE LOGITS
     คํา
    0.46
     fuga
    0.43
     bezahlen
    0.42
    ("'
    0.41
     목적
    0.41
     เป้า
    0.40
     수를
    0.40
     എന്നാല്‍
    0.40
     emptied
    0.39
     emptying
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.