© 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. 138858
    Prev
    Next
    INDEX
    Explanations

    remains constant; lost; might be; you can; fields; rejoice in

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

    conceptual, technical, programming, object

    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
    ن
    0.53
    log
    0.48
    し
    0.48
    a
    0.48
    松
    0.47
    ጥ
    0.47
    not
    0.46
    پ
    0.46
    内
    0.46
    興趣
    0.45
    POSITIVE LOGITS
     membri
    0.51
     мам
    0.50
     bunların
    0.50
     elementos
    0.47
     CEOs
    0.46
     گوئیاں
    0.46
    iyaç
    0.46
     প্রতিনি
    0.46
     esemplari
    0.45
     proteína
    0.45
    Activations Density 0.000%

    No Known Activations