© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113901
    Prev
    Next
    INDEX
    Explanations

    secret detention, email stating

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

    it's a mood

    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
    Negative Logits
     तुम्हें
    0.54
    amini
    0.52
     तुम्हाला
    0.51
     bedre
    0.50
     бк
    0.50
     मिनिट
    0.49
     дать
    0.49
     तपाईं
    0.48
    👾
    0.48
     Warum
    0.48
    POSITIVE LOGITS
     unavoidable
    0.48
    결
    0.47
    문화
    0.46
    sharp
    0.46
    ெமி
    0.46
    ucar
    0.46
     rays
    0.45
     heights
    0.45
     engagement
    0.45
    supers
    0.45
    Activations Density 0.001%

    No Known Activations