© 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. 34201
    Prev
    Next
    INDEX
    Explanations

    too little or too much

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

    by the

    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
    損傷
    0.50
    ೆ
    0.48
    允
    0.45
    ми
    0.44
    飛
    0.44
    リエステル
    0.43
    玖
    0.43
     бу
    0.42
    љу
    0.42
    нке
    0.42
    POSITIVE LOGITS
     douze
    0.50
     moyen
    0.49
     ancienne
    0.49
    শ্যক
    0.48
     aard
    0.48
     partenariat
    0.48
     rø
    0.48
     alınd
    0.47
     échange
    0.47
     apar
    0.47
    Activations Density 0.000%

    No Known Activations