© 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. 123244
    Prev
    Next
    INDEX
    Explanations

    events and occasions

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

    cup or competition

    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
    <0x80>
    0.53
    );\
    0.47
    uther
    0.43
    Solic
    0.43
    ínio
    0.41
    tdp
    0.41
    норий
    0.41
    colorPrimary
    0.41
    vely
    0.40
    (())
    0.40
    POSITIVE LOGITS
     頭
    0.59
    ב
    0.59
     OVER
    0.55
     USE
    0.54
     incident
    0.54
     incidente
    0.54
     infusions
    0.52
     ajout
    0.51
     elapse
    0.51
     INDUST
    0.50
    Activations Density 0.000%

    No Known Activations