© 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. 76988
    Prev
    Next
    INDEX
    Explanations

    how when for whether

    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
    гие
    0.49
    начально
    0.46
    риста
    0.46
    ѐ
    0.46
    긴
    0.46
    emuan
    0.45
    fruits
    0.45
    емы
    0.44
     Watercolour
    0.44
    нави
    0.43
    POSITIVE LOGITS
     του
    0.46
    🫡
    0.45
     độc
    0.44
    ILI
    0.44
    並
    0.44
     جوئے
    0.43
     يتعلق
    0.42
    ME
    0.41
     පිළ
    0.41
    KH
    0.41
    Activations Density 0.002%

    No Known Activations