© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1845
    Prev
    Next
    INDEX
    Explanations

    javascript imports and configurations

    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
     нрави
    0.51
    ۔
    0.50
    ября
    0.49
    URNIZOR
    0.49
     třeba
    0.48
     lesión
    0.48
    领域
    0.47
    jelder
    0.47
    ؛
    0.47
     formé
    0.47
    POSITIVE LOGITS
     useDispatch
    0.52
     factorial
    0.50
     descendants
    0.49
     rejects
    0.48
     container
    0.48
     customers
    0.48
    ?',
    0.47
     goTo
    0.46
     C
    0.46
     useState
    0.46
    Activations Density 0.004%

    No Known Activations