© 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. 80171
    Prev
    Next
    INDEX
    Explanations

    key extraction

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

    states and follow-ups

    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
    т
    0.47
     trách
    0.46
    НО
    0.44
    ЕН
    0.44
    ை
    0.44
    ва
    0.44
    хай
    0.44
    РА
    0.43
    ភ
    0.43
    ха
    0.43
    POSITIVE LOGITS
     Differentiation
    0.55
     Websites
    0.49
    works
    0.49
     Friction
    0.48
    iform
    0.47
     Rel
    0.46
    mens
    0.46
     Practical
    0.46
     deterrence
    0.46
    rer
    0.46
    Activations Density 0.001%

    No Known Activations