© 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. 200494
    Prev
    Next
    INDEX
    Explanations

    pain in addition

    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
     the
    0.51
     brewing
    0.50
     africa
    0.48
    that
    0.47
     diatom
    0.45
    <0xA0>
    0.44
    frying
    0.44
    ম
    0.44
     ejection
    0.43
    hunting
    0.43
    POSITIVE LOGITS
    addTarget
    0.52
    жок
    0.50
     لذلك
    0.48
    šće
    0.47
     aproveitar
    0.47
     апре
    0.46
     Тран
    0.44
    Strafpunkte
    0.43
    ्री
    0.42
    اه
    0.42
    Activations Density 0.003%

    No Known Activations