© 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. 5063
    Prev
    Next
    INDEX
    Explanations

    contextual definitions and explanations of various words.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    describes state or relation

    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
     spooky
    0.46
     endothelium
    0.46
    ，
    0.46
     સંપૂર્ણ
    0.44
     spacers
    0.44
     externalities
    0.44
     ephemeral
    0.43
     incontinence
    0.43
     বিশেষ
    0.43
     instantiation
    0.43
    POSITIVE LOGITS
     причиной
    0.43
    ことにより
    0.41
     चाहिये
    0.41
     inoltre
    0.38
    }$.)
    0.38
    близи
    0.38
     terdapat
    0.37
    ಂತಹ
    0.37
     součas
    0.37
    徥
    0.37
    Activations Density 0.137%

    No Known Activations