© 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. 14213
    Prev
    Next
    INDEX
    Explanations

    related field

    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
     massless
    0.59
     LaTeX
    0.58
     Displaystyle
    0.57
     dangerously
    0.56
    тра
    0.55
     McDaniel
    0.54
    Ფ
    0.54
    дже
    0.53
     Booth
    0.52
     unsuccessfully
    0.52
    POSITIVE LOGITS
    s
    0.84
    t
    0.73
    y
    0.71
    o
    0.71
    line
    0.66
    yi
    0.66
     enzim
    0.66
    nome
    0.65
    link
    0.63
    ll
    0.62
    Activations Density 0.005%

    No Known Activations