© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 165045
    Prev
    Next
    INDEX
    Explanations

    know about National Survey not only

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

    sex is not always binary

    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
    yntax
    0.50
    yı
    0.48
    hire
    0.46
    ethane
    0.46
    perg
    0.46
    이드
    0.45
    šit
    0.45
    ')]
    0.44
    yll
    0.44
    ann
    0.44
    POSITIVE LOGITS
     a
    0.52
    ኬ
    0.52
     Orlando
    0.50
     ihe
    0.49
     annealing
    0.47
    佶
    0.46
     Ove
    0.46
     unmarried
    0.46
    কট
    0.46
    Orlando
    0.45
    Activations Density 0.000%

    No Known Activations