© 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. 148447
    Prev
    Next
    INDEX
    Explanations

    suddenly offers

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

    list items and descriptions

    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
    সভাপতি
    0.54
     근무
    0.52
     അവസാന
    0.50
     전통
    0.50
    軎
    0.50
     소련
    0.49
     கடைசி
    0.49
     건물
    0.48
     મતદાન
    0.47
     मतदान
    0.46
    POSITIVE LOGITS
    are
    0.48
     are
    0.43
     Centers
    0.42
     Hertfordshire
    0.41
     Shropshire
    0.41
     Recovery
    0.40
    (
    0.40
     Seattle
    0.39
     Center
    0.39
     Framework
    0.39
    Activations Density 0.000%

    No Known Activations