© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119480
    Prev
    Next
    INDEX
    Explanations

    functions that return values

    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_40_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
     Via
    0.42
    Margin
    0.40
    EM
    0.40
    ಲೆ
    0.38
     Near
    0.38
    F
    0.38
    Pic
    0.38
    Mood
    0.38
     источники
    0.38
     न
    0.37
    POSITIVE LOGITS
     cryptographic
    0.46
     facilitate
    0.43
     terrestrial
    0.42
     geophysical
    0.42
     kunna
    0.41
     fertil
    0.41
    avascript
    0.41
     reasonable
    0.41
     weaken
    0.40
     reused
    0.40
    Activations Density 0.015%

    No Known Activations