© 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. 168773
    Prev
    Next
    INDEX
    Explanations

    speaking from your perspective

    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
    o
    0.54
    Tower
    0.46
    u
    0.44
    nast
    0.44
    นิยม
    0.43
    his
    0.43
    因
    0.43
    Bra
    0.43
     অভাবে
    0.42
    Nelson
    0.41
    POSITIVE LOGITS
     Kontak
    0.50
     Variablen
    0.49
     Pollution
    0.48
     Kontakt
    0.48
    㗊
    0.47
     Entfer
    0.47
     डिवा
    0.47
     доклад
    0.46
     школу
    0.46
     Cadastro
    0.46
    Activations Density 0.001%

    No Known Activations