© 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. 228502
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     outperform
    0.44
     dearth
    0.44
     South
    0.43
     남
    0.43
     kvadrat
    0.42
     definition
    0.42
     kú
    0.41
     south
    0.41
     Ottoman
    0.41
     Tunes
    0.41
    POSITIVE LOGITS
    мою
    0.49
    ה
    0.47
    POSE
    0.47
    ഇ
    0.45
    Seit
    0.45
    an
    0.43
     세상
    0.43
     мире
    0.43
    𝓃
    0.43
     завжди
    0.42
    Activations Density 0.003%

    No Known Activations