© 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. 197781
    Prev
    Next
    INDEX
    Explanations

    service or reality

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

    infinite futures

    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
     HDPE
    0.55
     Regions
    0.54
     หน
    0.52
     mgr
    0.50
     čtyř
    0.50
     ért
    0.50
     cih
    0.50
     Ð
    0.50
     cantor
    0.50
     lt
    0.49
    POSITIVE LOGITS
    Situ
    0.56
    reality
    0.49
    прав
    0.49
    所
    0.49
    casus
    0.48
    機
    0.48
    ᔪ
    0.47
    𒁉
    0.47
     شدن
    0.46
    実
    0.46
    Activations Density 0.000%

    No Known Activations