© 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. 161107
    Prev
    Next
    INDEX
    Explanations

    programs

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

    technical data and examples

    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
    的游戏
    0.45
    पह
    0.43
    첫
    0.43
    business
    0.43
    annabin
    0.43
    产业链
    0.42
    开始
    0.42
    ধন
    0.41
    Ꮕ
    0.40
    quinazoline
    0.40
    POSITIVE LOGITS
     लोकांनी
    0.48
     ఎక్కువ
    0.47
     perturbations
    0.45
     escuelas
    0.44
     wrenches
    0.44
     refugees
    0.44
     satir
    0.44
     over
    0.42
     ئەو
    0.42
     captives
    0.41
    Activations Density 0.000%

    No Known Activations