© 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. 105646
    Prev
    Next
    INDEX
    Explanations

    links following certain words

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

    gendered descriptors

    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
    льнай
    0.49
     сеть
    0.47
    壯
    0.47
    Crist
    0.47
    ൃത്ത
    0.46
    ická
    0.46
     поступ
    0.46
    andon
    0.44
    azität
    0.43
    学家
    0.43
    POSITIVE LOGITS
     `<
    0.50
    t
    0.50
     appropriate
    0.50
     গৌরব
    0.46
     '<
    0.46
     golfing
    0.46
     SOS
    0.44
    d
    0.44
     subway
    0.43
     `{
    0.43
    Activations Density 0.000%

    No Known Activations