© 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. 28011
    Prev
    Next
    INDEX
    Explanations

    male / female candidates

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

    CMD instruction

    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
     Seni
    0.54
    🥰
    0.51
    !}
    0.51
    古屋
    0.50
    !");
    0.50
     🥰
    0.47
    !")
    0.46
     Agama
    0.46
     Fatima
    0.46
     Voj
    0.44
    POSITIVE LOGITS
     curr
    0.48
    icum
    0.48
     intérêts
    0.46
     optimization
    0.45
     trustworthiness
    0.45
     hydrocarbons
    0.45
     marriages
    0.44
    ଭ
    0.44
    analysis
    0.44
     interests
    0.43
    Activations Density 0.000%

    No Known Activations