© 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. 233650
    Prev
    Next
    INDEX
    Explanations

    shown in, feel drawn, undisputed failure

    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
     filesize
    0.49
     मैट्रिक्स
    0.47
    ファイル
    0.47
    ൭
    0.47
    colorChoice
    0.47
    ブロ
    0.46
     unitarity
    0.46
    ファイルを
    0.45
    лм
    0.44
    그러
    0.44
    POSITIVE LOGITS
     heavenly
    0.49
    era
    0.49
    ↵
    0.48
    -
    0.47
     rash
    0.47
     reside
    0.46
    rot
    0.45
    iks
    0.45
    inhua
    0.44
     FA
    0.44
    Activations Density 0.000%

    No Known Activations