© 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. 112134
    Prev
    Next
    INDEX
    Explanations

    various services and information

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

    gender and orientation

    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
    id
    0.59
    t
    0.54
    analysis
    0.52
    ສາມາດ
    0.51
    iss
    0.50
     rectify
    0.50
     analyse
    0.49
    ɪ
    0.48
    img
    0.48
    analyse
    0.47
    POSITIVE LOGITS
     Hospitality
    0.46
    ومه
    0.43
     Rodeo
    0.42
    酒店
    0.41
    ുകളിൽ
    0.41
     Journalism
    0.40
    اله
    0.40
    անում
    0.40
     Frau
    0.40
    で開催
    0.39
    Activations Density 0.004%

    No Known Activations