© 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. 9269
    Prev
    Next
    INDEX
    Explanations

    Foreign language content

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

    history, management, condition, keywords, optimization, 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
    たちが
    0.42
    1
    0.42
    5
    0.42
    实在是
    0.40
    ро
    0.39
    4
    0.39
    8
    0.39
    ic
    0.39
    ial
    0.39
    ile
    0.39
    POSITIVE LOGITS
     houve
    0.55
     też
    0.53
     Ayrıca
    0.53
     gehad
    0.49
     ayrıca
    0.49
    ابقه
    0.48
     Sereth
    0.48
     tiež
    0.47
     ook
    0.46
     manje
    0.44
    Activations Density 0.002%

    No Known Activations