© 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. 53-GEMMASCOPE-2-RES-262K
    7. 14710
    Prev
    Next
    INDEX
    Explanations

    describing current states or intentions

    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_53_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
    ទេ
    0.41
    ᱭ
    0.39
    constant
    0.37
    nier
    0.37
     Bola
    0.36
    constexpr
    0.36
    满
    0.35
    顧
    0.35
     undamaged
    0.34
    Bola
    0.34
    POSITIVE LOGITS
     proud
    0.57
     afraid
    0.55
     hoping
    0.54
     striving
    0.48
     Proud
    0.47
     willing
    0.46
     aiming
    0.46
     passionate
    0.45
    Proud
    0.45
     accustomed
    0.44
    Activations Density 0.044%

    No Known Activations