© 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. 147998
    Prev
    Next
    INDEX
    Explanations

    specific signed certificates

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

    density comparisons with feathers

    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
    든
    0.52
    ЕЛ
    0.50
    쐞
    0.49
    깜
    0.48
    èce
    0.46
    COOK
    0.46
    Spread
    0.45
     सृष्टि
    0.44
    弇
    0.44
    шед
    0.44
    POSITIVE LOGITS
     Japan
    0.48
     Fukuoka
    0.45
     ausgew
    0.42
     Publishing
    0.41
     Irving
    0.40
    :|
    0.40
     Organisation
    0.40
     Singapura
    0.40
     Tarant
    0.40
     Brigham
    0.40
    Activations Density 0.002%

    No Known Activations