© 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. 123909
    Prev
    Next
    INDEX
    Explanations

    search bar

    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
     Muitos
    0.50
     humiliated
    0.47
     священ
    0.46
    宽松
    0.46
     predominate
    0.45
     деятельность
    0.45
    数十
    0.45
    觅
    0.45
     extérieures
    0.44
     деятельности
    0.44
    POSITIVE LOGITS
    is
    0.61
    at
    0.59
    as
    0.58
    sa
    0.58
    b
    0.55
    z
    0.55
    el
    0.54
    aa
    0.53
    or
    0.52
    if
    0.52
    Activations Density 0.004%

    No Known Activations