© 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. 233795
    Prev
    Next
    INDEX
    Explanations

    class, risks, antibiotics, teaching

    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
     poss
    0.45
     পাবে
    0.44
    нициа
    0.44
     silencio
    0.43
     unsc
    0.43
    dessous
    0.42
     melewati
    0.41
    ẖ
    0.40
     funcion
    0.40
     hogi
    0.40
    POSITIVE LOGITS
     sprints
    0.50
    ignano
    0.48
    ander
    0.47
    ighed
    0.47
     autres
    0.47
    证实
    0.46
    转移
    0.44
     कुटु
    0.44
    什么是
    0.44
     যাবতীয়
    0.44
    Activations Density 0.002%

    No Known Activations