Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 31689
    Prev
    Next
    INDEX
    Explanations

    wheat germ, bran, yeast

    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_16_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
    r
    0.70
    k
    0.64
    อร์
    0.61
     acquist
    0.60
    w
    0.59
     regreso
    0.57
     semicolon
    0.57
     deserialize
    0.55
    𝐨
    0.55
    야
    0.54
    POSITIVE LOGITS
    '}
    0.71
     ,
    0.68
    OM
    0.68
    challenges
    0.66
    Wonderful
    0.66
     dív
    0.65
    }.
    0.64
    таж
    0.63
     ,'
    0.63
     \\..
    0.63
    Activations Density 0.003%

    No Known Activations