© 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. 14167
    Prev
    Next
    INDEX
    Explanations

    feminine colors and themes

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

    pink, blush, makeup

    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
     осуществля
    0.35
    of
    0.34
    {\'
    0.33
    the
    0.32
    student
    0.32
    सं
    0.32
    esehatan
    0.32
    state
    0.31
    strcmp
    0.31
    \'{
    0.31
    POSITIVE LOGITS
     pink
    0.47
     dolls
    0.46
     mermaid
    0.45
     filles
    0.45
     couleurs
    0.44
     PINK
    0.43
     girly
    0.43
     クリーム
    0.43
     pastel
    0.42
     Blush
    0.41
    Activations Density 0.000%

    No Known Activations