© 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. 175764
    Prev
    Next
    INDEX
    Explanations

    alternatives player products Software South balls

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

    list formatting and structure

    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
    ित
    0.49
     curvas
    0.47
    atan
    0.45
    ßer
    0.45
    iz
    0.45
     má
    0.44
    ífico
    0.44
    ب
    0.44
    är
    0.43
    ارة
    0.43
    POSITIVE LOGITS
     其他
    0.56
     computeEncoder
    0.52
     どう
    0.49
     ぞ
    0.49
     Το
    0.48
     נישט
    0.48
    clientsdetails
    0.47
    snd
    0.47
     herramient
    0.47
     অন্য
    0.46
    Activations Density 0.001%

    No Known Activations