© 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. 5635
    Prev
    Next
    INDEX
    Explanations

    mathematical problems and proofs

    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
    segaretro
    0.50
    뀔
    0.47
     бушлай
    0.46
    іга
    0.46
    RENDITION
    0.45
    솎
    0.45
    を獲得
    0.45
     ontwerp
    0.44
    ।’’
    0.44
    াদার
    0.44
    POSITIVE LOGITS
     problem
    0.64
     Problem
    0.56
    Problem
    0.55
    problem
    0.55
     supposed
    0.54
     nao
    0.53
    0.53
     p
    0.52
     problema
    0.52
     Proble
    0.52
    Activations Density 0.002%

    No Known Activations