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-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 697
    Prev
    Next
    INDEX
    Explanations

    Tofugu

    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
     means
    0.42
    творю
    0.39
     চালায়
    0.39
    󠁿
    0.39
    uerpo
    0.38
    																											
    0.38
     Substituting
    0.38
    ுடன்
    0.38
     '*
    0.37
    äum
    0.37
    POSITIVE LOGITS
    Tos
    0.62
     ટો
    0.57
    Toc
    0.54
    โท
    0.54
    Tob
    0.53
    TO
    0.53
     トー
    0.53
     Tó
    0.52
     Toc
    0.51
     Towa
    0.51
    Activations Density 0.035%

    No Known Activations