© 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. 76415
    Prev
    Next
    INDEX
    Explanations

    words and their common follow-ups

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

    code, list, calculation

    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
    INDIC
    0.46
    arev
    0.45
     elementi
    0.44
     sayfası
    0.44
    iseite
    0.44
     मनात
    0.44
    risis
    0.42
    ᛁ
    0.42
    芻
    0.41
     problemi
    0.41
    POSITIVE LOGITS
    คล
    0.46
     authenticated
    0.46
     Optimize
    0.44
     mát
    0.44
     transmissão
    0.44
     Transmission
    0.42
     Connectivity
    0.41
     optimized
    0.41
    ลา
    0.41
     inputStream
    0.41
    Activations Density 0.000%

    No Known Activations