© 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. 219815
    Prev
    Next
    INDEX
    Explanations

    life Plasma advanced technologies

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

    commands and scripting

    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
    зіно
    0.52
     aproximativ
    0.51
    욀
    0.51
     shouldUse
    0.50
    𒀀
    0.49
    تيب
    0.49
     atento
    0.49
    жды
    0.48
     lângă
    0.48
     japonais
    0.48
    POSITIVE LOGITS
    ud
    0.55
    in
    0.55
    ach
    0.55
    co
    0.55
    ect
    0.53
    RNA
    0.53
    shade
    0.53
     or
    0.52
    h
    0.52
    ac
    0.51
    Activations Density 0.003%

    No Known Activations