© 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. 83826
    Prev
    Next
    INDEX
    Explanations

    distance and time

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

    AI and OpenAI models

    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
    蠢
    0.50
    唱
    0.48
    讹
    0.48
    竞争
    0.44
    越来越
    0.43
    营收
    0.42
     increasingly
    0.42
    不已
    0.42
    职称
    0.42
    评论
    0.42
    POSITIVE LOGITS
    /
    0.53
     hijo
    0.51
     padres
    0.51
    輛
    0.49
     donor
    0.48
     padre
    0.47
     portability
    0.47
     المسافه
    0.47
     karn
    0.46
     plano
    0.46
    Activations Density 0.001%

    No Known Activations