© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6275
    Prev
    Next
    INDEX
    Explanations

    digits and names with numbers

    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_16_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
    ３
    0.58
    _
    0.54
    ５
    0.54
    itism
    0.48
    𝘬
    0.48
    ää
    0.47
    3
    0.46
    ían
    0.46
    ومی
    0.45
    ມັນ
    0.44
    POSITIVE LOGITS
    ש
    0.57
    re
    0.54
    ad
    0.54
    на
    0.54
    at
    0.52
    ות
    0.52
     Saltar
    0.52
    n
    0.50
    w
    0.49
    দ
    0.47
    Activations Density 0.573%

    No Known Activations