© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2038
    Prev
    Next
    INDEX
    Explanations

    divides into sufficient parts

    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
    ۔
    0.32
    ።
    0.31
    .“
    0.29
    .’’
    0.29
    エネルギー
    0.29
    .”
    0.28
     конститу
    0.28
    .’
    0.27
    ᱒
    0.27
     yeniden
    0.27
    POSITIVE LOGITS
     cukup
    0.42
     kilku
    0.40
    几次
    0.39
     dość
    0.38
     достаточно
    0.38
     काफी
    0.36
     عدة
    0.36
    多次
    0.35
    꽤
    0.35
     bastante
    0.35
    Activations Density 0.000%

    No Known Activations