© 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. 57516
    Prev
    Next
    INDEX
    Explanations

    murder, conspiracy, organizations, football, cute

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

    but clarify title places provided voltages

    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
    椏
    0.52
    خبر
    0.50
     Diagnose
    0.48
    唿
    0.48
     Respiratory
    0.48
    ماية
    0.47
     Diving
    0.46
    भीत
    0.46
    ף
    0.46
    ophageal
    0.46
    POSITIVE LOGITS
     കൂടി
    0.55
     murderous
    0.48
     murder
    0.48
     Сере
    0.48
    rylic
    0.46
     ද
    0.46
     conspir
    0.45
     கொலை
    0.45
     遅く
    0.45
     ს
    0.45
    Activations Density 0.000%

    No Known Activations