© 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. 223011
    Prev
    Next
    INDEX
    Explanations

    saved, cost, money, affordable

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

    list items or bullet points

    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
    දහ
    0.53
    دين
    0.45
    動
    0.45
    給我
    0.43
    แท
    0.43
    데이
    0.42
    داد
    0.42
    Entity
    0.41
    ধ
    0.41
    語
    0.41
    POSITIVE LOGITS
    hew
    0.46
     mantiene
    0.46
     autore
    0.46
     costruzione
    0.46
     grandmother
    0.46
     родствен
    0.46
     "&
    0.45
     diduga
    0.45
    [];
    0.45
     tecnica
    0.45
    Activations Density 0.001%

    No Known Activations