© 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. 108570
    Prev
    Next
    INDEX
    Explanations

    better understand and serve

    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
     πρώτη
    0.59
     makes
    0.57
     buona
    0.54
     é
    0.54
     scelte
    0.54
     buenas
    0.52
     fórmula
    0.52
     cleanest
    0.52
     برای
    0.51
     migliore
    0.50
    POSITIVE LOGITS
     commemorating
    0.46
    '})
    0.46
    textured
    0.45
     describing
    0.45
     representing
    0.43
    '}).
    0.43
     व्यक्त
    0.41
     புரிந்து
    0.40
    豐富
    0.40
    याच्या
    0.40
    Activations Density 0.031%

    No Known Activations