© 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. 50539
    Prev
    Next
    INDEX
    Explanations

    enumeration or list items

    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
     Unlike
    0.45
     unlike
    0.43
    Ⅶ
    0.40
    Unlike
    0.40
     likened
    0.40
     হিসাবে
    0.39
     aptly
    0.39
    သို့
    0.38
     LIKE
    0.38
    Ⅹ
    0.37
    POSITIVE LOGITS
    ITH
    0.45
     alguns
    0.41
    ith
    0.40
     काही
    0.39
    पि
    0.38
    重视
    0.38
    стройка
    0.38
    まずは
    0.38
     присутствует
    0.38
     کچھ
    0.37
    Activations Density 0.108%

    No Known Activations