© 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. 208221
    Prev
    Next
    INDEX
    Explanations

    communities, virus, animation

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

    asking questions and defining conditions

    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
     maneiras
    0.49
    텐
    0.46
    更有
    0.46
    shaders
    0.45
     atentos
    0.44
     claros
    0.42
    텍
    0.42
     EACH
    0.42
     semblables
    0.42
    래
    0.41
    POSITIVE LOGITS
     connaît
    0.56
     Nhân
    0.55
     Communities
    0.53
    <unused1046>
    0.49
     Neurog
    0.49
     আনুষ্ঠানিকভাবে
    0.49
     Nói
    0.48
     علاج
    0.48
     Virus
    0.47
     Animation
    0.47
    Activations Density 0.000%

    No Known Activations