© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52212
    Prev
    Next
    INDEX
    Explanations

    depict unsafe or specific lists

    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
    ებისა
    0.48
    йдз
    0.46
    鍖
    0.45
    莯
    0.45
    扱う
    0.44
    Ꭾ
    0.44
    mäß
    0.44
     podamos
    0.44
    работа
    0.44
     recibirá
    0.44
    POSITIVE LOGITS
    ↵↵
    0.49
     />
    0.46
     due
    0.46
     explains
    0.44
     confrontations
    0.43
    ;
    0.43
     insecurity
    0.41
    ↵↵↵↵
    0.41
    ；
    0.40
    ️
    0.40
    Activations Density 0.000%

    No Known Activations