© 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-65K
    7. 27674
    Prev
    Next
    INDEX
    Explanations

    asking questions, contributors, operators

    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_65k_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
    𝐞
    0.50
    ९
    0.46
     तीव्र
    0.45
    的思想
    0.45
     機械
    0.44
    शन
    0.44
    ceased
    0.43
     suffering
    0.43
    ЕТ
    0.43
     destroying
    0.42
    POSITIVE LOGITS
    T
    0.49
    Var
    0.48
     Usuarios
    0.46
    Usuarios
    0.44
    Settings
    0.44
    ]],
    0.44
     Sub
    0.43
    ErrorMessage
    0.43
    Survey
    0.43
     Tuscany
    0.43
    Activations Density 0.012%

    No Known Activations