© 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. 7805
    Prev
    Next
    INDEX
    Explanations

    making plans for

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

    little girl

    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
     Warsz
    0.35
     शैक्षणिक
    0.34
    {\
    0.34
    在
    0.34
     unserer
    0.34
    _
    0.34
    髙
    0.33
     Gutiérrez
    0.33
    ः
    0.33
     Aleks
    0.33
    POSITIVE LOGITS
     maken
    0.38
    merken
    0.32
    ᧐
    0.31
     marketers
    0.30
     copp
    0.29
    ADT
    0.29
     make
    0.28
    irati
    0.28
     کنی
    0.28
    ߋ
    0.28
    Activations Density 0.026%

    No Known Activations