© 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. 17671
    Prev
    Next
    INDEX
    Explanations

    out of

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

    out of bounds or range

    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
    ÉT
    0.52
     aldı
    0.51
     Mehndi
    0.50
    FFECT
    0.50
     tématu
    0.49
     তিনিও
    0.49
    Iniciar
    0.49
    ل
    0.49
    োধন
    0.49
    ูด
    0.49
    POSITIVE LOGITS
     out
    1.08
    out
    0.87
     Out
    0.80
    outof
    0.77
    出
    0.76
    出的
    0.71
    outs
    0.71
     outta
    0.71
    Out
    0.70
     OUT
    0.70
    Activations Density 0.132%

    No Known Activations