© 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. 141589
    Prev
    Next
    INDEX
    Explanations

    framed artwork

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

    definitions 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
     cutters
    0.46
     days
    0.44
     droughts
    0.44
    ’
    0.44
     ellipsoid
    0.44
    V
    0.42
     реакции
    0.42
    reath
    0.41
     trips
    0.40
    crest
    0.40
    POSITIVE LOGITS
     comunicazione
    0.48
     використа
    0.48
    gnię
    0.47
     pertence
    0.47
    丅
    0.47
     বাঙ্গালার
    0.46
     díky
    0.45
     deviceInfo
    0.45
    বসাইট
    0.45
     മാലി
    0.45
    Activations Density 0.000%

    No Known Activations