© 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. 77093
    Prev
    Next
    INDEX
    Explanations

    expensive things

    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
    out
    0.48
    Join
    0.46
    unico
    0.45
    ے
    0.44
    ę
    0.43
    <unused64>
    0.43
    Mart
    0.43
     mondo
    0.42
     carc
    0.42
     furnishings
    0.42
    POSITIVE LOGITS
     BVHTree
    0.51
    ?>"
    0.48
     устойчи
    0.47
    aniyam
    0.47
    ATIVE
    0.46
    AUTHORIZED
    0.45
     教え
    0.44
    𝑛
    0.44
     Саша
    0.42
    <unused722>
    0.42
    Activations Density 0.003%

    No Known Activations