© 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. 15109
    Prev
    Next
    INDEX
    Explanations

    saying specific phrases like "yes" or "no"

    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
     Riemannian
    0.62
     (
    0.61
    ל
    0.60
    ដើម្បី
    0.59
    ب
    0.57
     to
    0.55
     Interpre
    0.55
     Reasoning
    0.55
     Shouldn
    0.54
    ي
    0.54
    POSITIVE LOGITS
     goodbye
    0.64
     bienvenidos
    0.59
    gı
    0.58
     сказать
    0.57
    g
    0.56
    that
    0.54
    ای
    0.54
     say
    0.54
    gın
    0.52
     rằng
    0.52
    Activations Density 0.024%

    No Known Activations