© 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. 174919
    Prev
    Next
    INDEX
    Explanations

    information they

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

    individual motivation resentment Intelligence Shock

    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
    ้าม
    0.51
    體
    0.50
    ان
    0.47
    ↵
    0.45
     "
    0.44
    Taste
    0.44
    Volume
    0.44
    ��
    0.43
    ليف
    0.43
    Nothing
    0.43
    POSITIVE LOGITS
     Bạch
    0.52
     ngồi
    0.51
     rất
    0.50
     lovingly
    0.50
     ල
    0.49
     öz
    0.49
    cdZ
    0.49
     यानी
    0.48
     wavenumber
    0.48
    bella
    0.48
    Activations Density 0.000%

    No Known Activations