© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126366
    Prev
    Next
    INDEX
    Explanations

    legal or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    基
    0.56
    估
    0.55
    ن
    0.52
    жидан
    0.51
    Ј
    0.48
    К
    0.48
    жде
    0.48
     emocion
    0.46
    荿
    0.46
    信
    0.46
    POSITIVE LOGITS
    lineWidth
    0.54
    ्याच्या
    0.46
    raient
    0.45
    ool
    0.44
    erville
    0.43
    arnataka
    0.43
    municipal
    0.43
    would
    0.43
    parts
    0.43
     रझा
    0.43
    Activations Density 0.002%

    No Known Activations