© 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. 196017
    Prev
    Next
    INDEX
    Explanations

    honesty and truth

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

    Printing, do, the, 1, things

    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
     parish
    0.57
    EL
    0.48
     administrative
    0.48
     Parish
    0.48
    uss
    0.47
    ##
    0.46
    כי
    0.46
     serum
    0.46
     सेंट
    0.46
    s
    0.44
    POSITIVE LOGITS
     শাস্ত্র
    0.52
    ження
    0.51
     Voraussetzungen
    0.50
     beginnetje
    0.50
     冖
    0.49
     அளவில்
    0.48
     allongé
    0.48
     cử
    0.48
     интер
    0.47
    RefItem
    0.47
    Activations Density 0.001%

    No Known Activations