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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6978
    Prev
    Next
    INDEX
    Explanations

    provide several

    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
    bit
    0.44
     (
    0.44
    ปัจ
    0.41
    pace
    0.40
     
    0.40
    のである
    0.39
    prec
    0.39
    operand
    0.39
     ಈ
    0.38
     confounding
    0.38
    POSITIVE LOGITS
     animaux
    0.52
    ات
    0.51
     setDescription
    0.50
     animals
    0.50
     ouvrir
    0.49
    يه
    0.48
     لكن
    0.48
     invertebrates
    0.48
     käyt
    0.48
     crossbow
    0.48
    Activations Density 0.038%

    No Known Activations