© 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. 109770
    Prev
    Next
    INDEX
    Explanations

    hope survives

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

    further north, extract true

    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
     توص
    0.51
    而不
    0.47
    婺
    0.47
    所以我
    0.47
    所以在
    0.46
     widers
    0.44
    ли
    0.43
     избра
    0.43
     اهلا
    0.43
     Obwohl
    0.43
    POSITIVE LOGITS
    ᴜ
    0.50
     乗
    0.48
    ᴛ
    0.46
    older
    0.45
     pathogenic
    0.45
     हानिकारक
    0.44
     ascertaining
    0.44
    ASY
    0.44
     surfboard
    0.44
    𝘤
    0.43
    Activations Density 0.000%

    No Known Activations