© 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. 157726
    Prev
    Next
    INDEX
    Explanations

    REQUEST command

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

    seductive, sex, sexy

    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
     invasions
    0.47
    sheep
    0.46
    nord
    0.44
     I
    0.42
    綴
    0.42
    ampa
    0.42
    لب
    0.42
    jumping
    0.42
    لق
    0.41
     আওয়
    0.40
    POSITIVE LOGITS
     REQUEST
    0.60
     requête
    0.54
     например
    0.48
    㸽
    0.48
     בכל
    0.47
    檤
    0.47
    ività
    0.46
     complètement
    0.46
     stycznia
    0.45
    ছে
    0.45
    Activations Density 0.000%

    No Known Activations