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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8476
    Prev
    Next
    INDEX
    Explanations

    starting clauses with 'while' or 'once'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     هو
    0.59
    ವುದು
    0.57
    ść
    0.54
     duquel
    0.53
     correlates
    0.52
     Flugh
    0.52
    <0xBA>
    0.51
    的是
    0.51
    <0xA1>
    0.50
    oudre
    0.50
    POSITIVE LOGITS
    யில்
    0.58
    offic
    0.58
    ти
    0.52
    an
    0.51
    诟
    0.51
    eight
    0.50
    fär
    0.50
    us
    0.48
    på
    0.48
    OOP
    0.47
    Activations Density 0.186%

    No Known Activations