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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113066
    Prev
    Next
    INDEX
    Explanations

    reading, measurement, estimation

    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
     SQUARE
    0.49
    ক্সি
    0.46
     gobierno
    0.45
    Korean
    0.44
    緻
    0.44
     korean
    0.44
    Quem
    0.44
     komponen
    0.43
    Ố
    0.43
    French
    0.43
    POSITIVE LOGITS
    leri
    0.52
    ла
    0.52
    ises
    0.50
    inars
    0.49
    genic
    0.48
    ları
    0.47
    cations
    0.47
     outbursts
    0.47
    lal
    0.46
    ments
    0.46
    Activations Density 0.001%

    No Known Activations