© 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. 223093
    Prev
    Next
    INDEX
    Explanations

    receiving or status check

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

    technical terms explained

    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
    ૃહ
    0.50
    理由
    0.46
     отзы
    0.45
     amelior
    0.44
     escalate
    0.42
     இணைப்பு
    0.42
    ѐ
    0.41
     analizar
    0.41
     efectivamente
    0.40
     ரி
    0.40
    POSITIVE LOGITS
    ล
    0.55
    uv
    0.50
     lö
    0.49
    iyev
    0.48
    ri
    0.48
    ippy
    0.47
    堬
    0.46
    скі
    0.46
    ړ
    0.46
    शिप
    0.45
    Activations Density 0.000%

    No Known Activations