© 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. 222541
    Prev
    Next
    INDEX
    Explanations

    Hello Dave, defined, HMPE

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

    theory predicts

    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
     словам
    0.53
    waitKey
    0.45
    م
    0.45
    ..”
    0.43
     Toh
    0.43
     πίνακα
    0.43
     Aussage
    0.43
     அற்புத
    0.43
     टू
    0.43
     glauben
    0.43
    POSITIVE LOGITS
    WEEK
    0.47
    وانی
    0.46
    িয়াই
    0.46
    ３
    0.46
    вары
    0.45
     candidate
    0.45
    ване
    0.43
     Candidate
    0.43
     Mamm
    0.42
     ~\
    0.42
    Activations Density 0.001%

    No Known Activations