© 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. 168746
    Prev
    Next
    INDEX
    Explanations

    date and events

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

    how something is done

    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
    gebaut
    0.52
     panjang
    0.48
    巧
    0.47
     sempre
    0.46
     riscos
    0.46
    蘭
    0.45
     sicurezza
    0.45
    categorias
    0.45
     portata
    0.45
     وا
    0.45
    POSITIVE LOGITS
     étrang
    0.47
    roleum
    0.45
    文艺
    0.44
     ngram
    0.44
     Hz
    0.43
     चम्म
    0.43
    ască
    0.43
    //"
    0.42
    ৈর
    0.42
    astery
    0.42
    Activations Density 0.000%

    No Known Activations