© 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. 73056
    Prev
    Next
    INDEX
    Explanations

    throne twice

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

    Network ACLs

    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
     የተለያዩ
    0.52
     અમારી
    0.50
     हर
    0.49
     නමුත්
    0.48
     幅
    0.48
     මු
    0.47
     photographed
    0.47
     则
    0.46
     revê
    0.46
     ကု
    0.46
    POSITIVE LOGITS
    Экс
    0.51
    Lower
    0.50
    Lar
    0.50
     czek
    0.49
    Lav
    0.48
     Theft
    0.48
     Parcel
    0.47
    ใส
    0.46
    El
    0.46
    ї
    0.46
    Activations Density 0.000%

    No Known Activations