© 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. 165953
    Prev
    Next
    INDEX
    Explanations

    abnormal financing, breach of

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

    government responsibilities and citizen safety

    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
     período
    0.52
     só
    0.48
     spoonful
    0.47
     oblasti
    0.46
    ំណ
    0.45
     rá
    0.45
     períodos
    0.44
     女
    0.44
     最
    0.44
     žena
    0.44
    POSITIVE LOGITS
     Проци
    0.51
     Intelli
    0.48
    Whe
    0.48
     উপস্থাপন
    0.46
    ()'
    0.45
    تھی
    0.45
    Off
    0.45
    Veh
    0.45
    架构
    0.45
     Vort
    0.44
    Activations Density 0.001%

    No Known Activations