© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1405
    Prev
    Next
    INDEX
    Explanations

    within it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     sequentially
    1.10
     무슨
    1.03
     worrisome
    0.99
    ᚕ
    0.99
     semnific
    0.99
    왤
    0.98
     meaningful
    0.98
    തിരെ
    0.98
     কতকগুলি
    0.98
     relatively
    0.98
    POSITIVE LOGITS
    该
    0.79
    該
    0.73
     the
    0.72
    it
    0.68
     acestea
    0.67
    はその
    0.67
    ())
    0.67
    our
    0.65
    ()
    0.64
    glow
    0.64
    Activations Density 0.898%

    No Known Activations