© 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. 111349
    Prev
    Next
    INDEX
    Explanations

    Valentine's Day or romantic themes

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

    non-explicit romance and love

    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
     алюми
    0.48
    幅度
    0.47
     нефте
    0.46
    碁
    0.44
    🖐
    0.44
    номет
    0.44
    囷
    0.42
    体操
    0.42
     डीजल
    0.42
     adjusts
    0.41
    POSITIVE LOGITS
     romantic
    1.48
     romant
    1.40
     Valentines
    1.39
     Valentine
    1.35
     valentines
    1.31
     Romantic
    1.28
     valentine
    1.27
     romance
    1.25
    Valentine
    1.22
    romantic
    1.18
    Activations Density 0.274%

    No Known Activations