© 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. 98242
    Prev
    Next
    INDEX
    Explanations

    conditional logic

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

    conditional feature enabling

    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
    troop
    0.44
     yp
    0.42
     वाजिब
    0.40
     stronie
    0.37
     ALLEN
    0.37
     φορά
    0.37
    Allen
    0.36
    ++];
    0.36
     এমনি
    0.36
    thr
    0.36
    POSITIVE LOGITS
     मधु
    0.43
     पाठशाला
    0.42
    希望
    0.41
     ENABLE
    0.41
     appendices
    0.41
    厌
    0.40
     multiuser
    0.40
     !
    0.40
    abulary
    0.40
     USE
    0.40
    Activations Density 0.021%

    No Known Activations