© 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. 88355
    Prev
    Next
    INDEX
    Explanations

    pixel person

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

    urban exploration

    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
    endela
    0.46
    过
    0.46
    出荷
    0.46
    自家
    0.46
    ファミリー
    0.46
    练习
    0.45
    驯
    0.45
    ARTS
    0.45
    ق
    0.45
    नाइट
    0.44
    POSITIVE LOGITS
     muốn
    0.52
     miền
    0.52
     Pir
    0.49
     loài
    0.49
     {'
    0.48
     Mig
    0.48
     Jor
    0.48
     vê
    0.47
     collectif
    0.47
     xứ
    0.46
    Activations Density 0.000%

    No Known Activations