© 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. 13597
    Prev
    Next
    INDEX
    Explanations

    additional or more

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

    disclaimers and common advice

    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
    yled
    0.44
    ಗ್ಗೆ
    0.41
     ওয়েবসাইট
    0.40
    adays
    0.39
    trex
    0.39
     :',
    0.38
    ∶
    0.37
     (".
    0.37
    ተር
    0.36
    ́
    0.36
    POSITIVE LOGITS
     మరింత
    0.69
     zusätz
    0.59
     আরও
    0.57
    以外の
    0.56
     autres
    0.55
     supplémentaire
    0.55
     adicionales
    0.54
     tambahan
    0.54
     supplémentaires
    0.53
     zusätzliche
    0.53
    Activations Density 0.188%

    No Known Activations