© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120314
    Prev
    Next
    INDEX
    Explanations

    division and ratios

    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
     -
    0.46
     frac
    0.43
    frac
    0.42
     =
    0.40
     dependiendo
    0.38
    탐
    0.37
    1
    0.37
     Nin
    0.35
    2
    0.35
     can
    0.35
    POSITIVE LOGITS
    මාණය
    0.44
    ház
    0.42
    ຄວາມ
    0.42
    Sang
    0.41
     Kwame
    0.40
    魑
    0.40
     kaha
    0.40
    ңыз
    0.40
    Magnetic
    0.39
    Kamu
    0.39
    Activations Density 0.014%

    No Known Activations