© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3575
    Prev
    Next
    INDEX
    Explanations

    file path and image features

    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_40_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
    슭
    0.33
    Ꭳ
    0.30
    geqslant
    0.29
    Despatx
    0.29
     Мне
    0.28
     sheath
    0.28
    ူး
    0.27
     行っ
    0.27
    Ꮔ
    0.27
    Therates
    0.26
    POSITIVE LOGITS
    in
    0.34
    online
    0.29
    an
    0.29
    features
    0.29
    os
    0.28
     Online
    0.28
    ad
    0.28
     Global
    0.28
    den
    0.27
    la
    0.27
    Activations Density 0.052%

    No Known Activations