© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2244
    Prev
    Next
    INDEX
    Explanations

    indicate purpose or action

    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_16_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
     في
    0.86
    ।
    0.77
     in
    0.75
     الاجتماعي
    0.68
     sliced
    0.67
     بسي
    0.66
     locais
    0.66
     وغير
    0.66
     médicos
    0.65
     ganzen
    0.64
    POSITIVE LOGITS
    ก
    0.86
    0.81
    ک
    0.72
    գ
    0.72
    बद्ध
    0.69
    ब
    0.69
    л
    0.67
    ע
    0.66
    A
    0.66
    기
    0.65
    Activations Density 0.457%

    No Known Activations