© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions or calculations

    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
    langan
    0.44
    тени
    0.43
    ława
    0.43
     азо
    0.43
    лан
    0.43
    лося
    0.42
    晧
    0.42
    榉
    0.41
    法施行
    0.41
    Ꮀ
    0.41
    POSITIVE LOGITS
     __
    0.45
    8
    0.44
    5
    0.43
    ^
    0.41
    ....
    0.41
     Sorry
    0.41
     Garbage
    0.39
    SM
    0.39
     sorry
    0.39
    ⌣
    0.39
    Activations Density 0.001%

    No Known Activations