© 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. 115699
    Prev
    Next
    INDEX
    Explanations

    senior thesis

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

    objectification and sexual use

    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
     dereg
    0.43
    <strong>
    0.41
     terribly
    0.41
     frequented
    0.41
    aha
    0.40
    льника
    0.39
    дуу
    0.39
    ри
    0.39
    hna
    0.39
    adakan
    0.39
    POSITIVE LOGITS
     unité
    0.50
     afbeelding
    0.49
    œurs
    0.49
     اختلافات
    0.49
    滥
    0.49
     responsabilité
    0.48
     القض
    0.47
     compétences
    0.47
     보호
    0.47
     시간
    0.47
    Activations Density 0.001%

    No Known Activations