© 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-65K
    7. 48934
    Prev
    Next
    INDEX
    Explanations

    specific instances and descriptions

    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_65k_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
    だけで
    0.49
    ریب
    0.40
    ))).
    0.38
     пони
    0.38
    !)
    0.38
    )):
    0.38
    पूर्व
    0.38
     온
    0.37
    度の
    0.37
     কূটনীতিক
    0.37
    POSITIVE LOGITS
     arquivo
    0.58
     dió
    0.51
    ляє
    0.47
     Pó
    0.47
     Cour
    0.47
     Smith
    0.47
     Cornell
    0.47
     Ratch
    0.46
     Bloch
    0.46
     Mills
    0.45
    Activations Density 0.003%

    No Known Activations