© 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. 115864
    Prev
    Next
    INDEX
    Explanations

    finding a phrase

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

    languages and translation quality

    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
     Secret
    0.51
    ogue
    0.47
     secret
    0.44
    ,
    0.44
     Real
    0.43
     little
    0.43
     gun
    0.42
     Little
    0.42
     DD
    0.42
    reliance
    0.42
    POSITIVE LOGITS
    ке
    0.61
    ブラック
    0.57
     мають
    0.57
    ீ
    0.56
     природ
    0.55
    фа
    0.55
    ettivi
    0.55
    ک
    0.55
     ПРО
    0.54
    injlim
    0.54
    Activations Density 0.000%

    No Known Activations