© 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. 1947
    Prev
    Next
    INDEX
    Explanations

    actual or real things

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

    actual state or output

    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
     erythematosus
    0.43
     cuadrado
    0.39
     jay
    0.38
    সারণ
    0.37
    升级
    0.37
     ഉയ
    0.36
     उछ
    0.36
    皱
    0.36
     supervivencia
    0.36
     повышение
    0.36
    POSITIVE LOGITS
     actual
    1.01
    実際に
    0.99
     실제
    0.95
    实际
    0.93
    實際
    0.93
    実際の
    0.93
    actual
    0.91
     Actual
    0.88
    Actual
    0.86
     실제로
    0.83
    Activations Density 0.276%

    No Known Activations