© 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. 74186
    Prev
    Next
    INDEX
    Explanations

    awards, recognition, ranked, certified

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

    awards and recognition

    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
    fections
    0.44
    求
    0.42
    গুলোকে
    0.42
    critic
    0.40
    ACES
    0.40
     breakdowns
    0.39
    i
    0.39
    ình
    0.38
    c
    0.38
    hero
    0.38
    POSITIVE LOGITS
     sayesinde
    0.64
     благодаря
    0.54
     vanwege
    0.54
    凭借
    0.52
    这意味着
    0.52
     നേടിയ
    0.52
     dzięki
    0.51
     Malgré
    0.51
     номером
    0.50
     aufgrund
    0.50
    Activations Density 0.255%

    No Known Activations