© 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. 144160
    Prev
    Next
    INDEX
    Explanations

    understanding concepts and requirements

    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
    т
    0.54
    }"
    0.52
    يو
    0.50
    ت
    0.49
     pól
    0.47
    t
    0.44
    ldots
    0.44
    ز
    0.43
     na
    0.42
    *}\
    0.42
    POSITIVE LOGITS
     cords
    0.52
    āda
    0.50
     microarray
    0.49
    皞
    0.49
    ņem
    0.48
    ėti
    0.47
    प्रीत
    0.47
     kijken
    0.47
     predation
    0.46
    pthread
    0.46
    Activations Density 0.002%

    No Known Activations