© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6410
    Prev
    Next
    INDEX
    Explanations

    Fortran code blocks

    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
    f
    0.86
    v
    0.76
    st
    0.71
    ך
    0.71
    t
    0.70
    ner
    0.69
    g
    0.68
    are
    0.64
    sk
    0.64
    ها
    0.63
    POSITIVE LOGITS
    이드
    0.66
    更
    0.62
    К
    0.61
    Zs
    0.61
    Д
    0.61
    ),'
    0.60
    ZIE
    0.58
     effectuées
    0.58
    })^{
    0.57
    ejs
    0.57
    Activations Density 0.003%

    No Known Activations