© 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. 93778
    Prev
    Next
    INDEX
    Explanations

    concepts and their breakdown

    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
     detn
    0.44
     syncing
    0.44
     क्रीम
    0.44
    ㎠
    0.44
     rectangles
    0.44
     چک
    0.44
     punctures
    0.43
    ಾಗಿತ್ತು
    0.43
     neutrinos
    0.43
     methylation
    0.43
    POSITIVE LOGITS
    el
    0.55
    ]
    0.54
    u
    0.53
    mos
    0.46
    k
    0.45
    le
    0.44
    ml
    0.43
    li
    0.43
    ก
    0.43
    AL
    0.43
    Activations Density 0.002%

    No Known Activations