© 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. 152457
    Prev
    Next
    INDEX
    Explanations

    instructions, suggestions, or requests

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

    asking for information or interaction

    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
     دارد
    0.63
     داره
    0.57
     используется
    0.56
     दिसते
    0.54
    ಗಳಿವೆ
    0.53
     betroffen
    0.50
     ነበር
    0.49
    𝚃
    0.49
     دارند
    0.49
    زمانہ
    0.49
    POSITIVE LOGITS
     hãy
    0.54
    Hãy
    0.48
    していく
    0.48
    请
    0.47
     Hãy
    0.47
     请
    0.46
     Санкт
    0.44
    expand
    0.44
    하면
    0.43
    しましょう
    0.43
    Activations Density 0.001%

    No Known Activations