© 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. 2242
    Prev
    Next
    INDEX
    Explanations

    special tokens or delimiters

    np_acts-logits-general · gemini-2.5-flash-lite

    segments of example data or outputs within instructional/code snippets, especially quoted strings, array/list literals, and other sample content.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     necro
    0.37
     Salts
    0.37
     capsid
    0.35
    ிறது
    0.34
     fato
    0.32
     adqu
    0.32
     杨
    0.32
     telep
    0.32
    ويلة
    0.31
     setia
    0.31
    POSITIVE LOGITS
    想要
    0.37
    に対して
    0.37
    смотреть
    0.37
    one
    0.36
    texte
    0.35
    に対し
    0.34
    よ
    0.34
    それを
    0.34
    want
    0.34
    さて
    0.34
    Activations Density 0.359%

    No Known Activations