© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25093
    Prev
    Next
    INDEX
    Explanations

    related to lists, actions, or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    Azure AD Connect and crops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تیاری
    0.54
    пами
    0.54
    仮
    0.51
    ảnh
    0.50
    び
    0.49
    ểm
    0.49
    मा
    0.48
    ки
    0.47
    ình
    0.47
    さを
    0.46
    POSITIVE LOGITS
     VOICE
    0.53
     biochem
    0.50
     romant
    0.50
     dramat
    0.48
     approached
    0.46
     toc
    0.46
    .[[
    0.46
     peck
    0.46
     realiz
    0.45
     vytvá
    0.45
    Activations Density 0.000%

    No Known Activations