© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82987
    Prev
    Next
    INDEX
    Explanations

    song download

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

    action vs happening

    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
     दत्ता
    0.46
    ☦
    0.45
    ในการ
    0.45
    が得
    0.44
    一场
    0.43
     अंशु
    0.43
     зміни
    0.43
    厘
    0.42
    欬
    0.41
     Stomach
    0.41
    POSITIVE LOGITS
     blurring
    0.55
     dude
    0.55
     worker
    0.53
     trooper
    0.52
     district
    0.50
    viation
    0.49
    district
    0.48
     terci
    0.47
     ustedes
    0.47
     baz
    0.47
    Activations Density 0.000%

    No Known Activations