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. 19517
    Prev
    Next
    INDEX
    Explanations

    document format designs

    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
     싶
    0.44
     adquisición
    0.43
     በላይ
    0.42
     acquire
    0.42
    েলার
    0.40
    処理
    0.39
     dés
    0.39
     idempot
    0.39
     recyclable
    0.39
     guaranteed
    0.39
    POSITIVE LOGITS
    დნენ
    0.49
    +](=
    0.47
    Siehe
    0.46
    note
    0.46
    щал
    0.43
     crouching
    0.41
     사람은
    0.40
    attribute
    0.40
    See
    0.39
    hitth
    0.39
    Activations Density 0.001%

    No Known Activations