© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3142
    Prev
    Next
    INDEX
    Explanations

    Thai, Spanish, Catalan, Swedish, Indonesian, English and other languages

    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
    RENDITION
    0.31
    귿
    0.30
     事業
    0.29
    IVERSITY
    0.29
    ULTURAL
    0.29
     tabpos
    0.29
    UNICATIONS
    0.28
    REGIUNE
    0.28
    ⟋
    0.28
    VENTION
    0.28
    POSITIVE LOGITS
     
    0.31
    et
    0.31
     you
    0.28
    o
    0.28
    h
    0.27
    c
    0.27
    ,
    0.26
    an
    0.25
    aaa
    0.25
    ed
    0.24
    Activations Density 0.056%

    No Known Activations