© 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. 78772
    Prev
    Next
    INDEX
    Explanations

    women gathering and discussing change

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

    lingerie and undergarments

    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
    nde
    0.54
    i
    0.52
    തി
    0.49
    ille
    0.49
    ed
    0.48
    Country
    0.46
    st
    0.46
    ments
    0.45
    stit
    0.45
    mber
    0.45
    POSITIVE LOGITS
     exhibitions
    0.48
    $/../../
    0.47
    మ్యాచ్
    0.46
     FITNESS
    0.46
     girlfriends
    0.45
    جیت
    0.45
     females
    0.44
     обуча
    0.44
     playroom
    0.44
     акчага
    0.43
    Activations Density 0.001%

    No Known Activations