© 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. 125090
    Prev
    Next
    INDEX
    Explanations

    childcare sitter womb

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

    focus on or web UI

    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
    curvature
    0.52
    ние
    0.51
    名の
    0.50
     её
    0.50
     ее
    0.49
    금
    0.48
    irió
    0.48
    FileUpload
    0.47
    spreading
    0.47
    ルの
    0.47
    POSITIVE LOGITS
     pul
    0.53
     womb
    0.47
     chil
    0.45
     gpm
    0.45
     bodysuit
    0.45
     poch
    0.43
     lega
    0.43
     sitter
    0.43
    。
    0.43
     chiller
    0.42
    Activations Density 0.001%

    No Known Activations