© 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. 53058
    Prev
    Next
    INDEX
    Explanations

    areas of communities

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

    demonstrations, single applications, skin under

    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
    霸
    0.44
    、
    0.44
    0.42
     pression
    0.41
    !,
    0.40
    一组
    0.40
    壓
    0.39
    ۰
    0.39
    êtes
    0.38
    Nothing
    0.38
    POSITIVE LOGITS
     TRAILS
    0.49
    GUNDABAD
    0.46
    सेवी
    0.46
    ULTURE
    0.45
     はい
    0.44
    oufl
    0.44
    ীভূত
    0.43
    ্যস্ত
    0.43
    ালা
    0.43
     Bildern
    0.43
    Activations Density 0.000%

    No Known Activations