© 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. 200015
    Prev
    Next
    INDEX
    Explanations

    own their, caused or

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

    internal use or unethical

    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
    ;
    0.57
    <0x0D>
    0.51
     caught
    0.51
    ’
    0.51
    caught
    0.50
    0.49
    '
    0.48
     creates
    0.47
    0.47
     needs
    0.47
    POSITIVE LOGITS
    擀
    0.51
    мії
    0.50
    ماً
    0.49
    ましい
    0.49
    व्यक्त
    0.48
    птовалю
    0.47
    валася
    0.47
     SCIENCE
    0.47
    фек
    0.46
    醀
    0.46
    Activations Density 0.000%

    No Known Activations