Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 20621
    Prev
    Next
    INDEX
    Explanations

    rational, Gothic, or tarot readings

    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_40_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
    ḩ
    0.39
    rapati
    0.38
    issantes
    0.37
    ériment
    0.36
    ێن
    0.36
    ຫວ
    0.36
     enlarging
    0.36
    嗣
    0.36
     Sanger
    0.36
    hass
    0.35
    POSITIVE LOGITS
     racional
    0.41
    шем
    0.39
     rational
    0.37
     bt
    0.37
    Dynam
    0.37
     estar
    0.37
     gothic
    0.36
     рациона
    0.36
     Tact
    0.36
     Gothic
    0.36
    Activations Density 0.000%

    No Known Activations