© 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. 239637
    Prev
    Next
    INDEX
    Explanations

    online services and information

    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
     conteú
    0.52
    馅
    0.46
    []{
    0.45
     נא
    0.45
     enthal
    0.43
    をお願い
    0.43
     niña
    0.43
    NSInteger
    0.43
     factorización
    0.43
    ங
    0.42
    POSITIVE LOGITS
    burnt
    0.48
    fired
    0.47
    press
    0.46
    feather
    0.46
    varying
    0.46
    limit
    0.45
    asted
    0.44
    vent
    0.44
    kept
    0.44
    otrex
    0.44
    Activations Density 0.000%

    No Known Activations