© 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. 26139
    Prev
    Next
    INDEX
    Explanations

    Hall of Fame inductions

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

    Hall of Fame inductees

    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
    濘
    0.44
     localisation
    0.44
     distributive
    0.43
     นาย
    0.42
     derivative
    0.42
    ˧
    0.42
    ATIVE
    0.41
     ayah
    0.41
    賞
    0.40
    лаве
    0.40
    POSITIVE LOGITS
     retirees
    0.56
     Retire
    0.54
     retiring
    0.50
     Retired
    0.50
     Adirond
    0.48
    Retired
    0.46
     कक्ष
    0.46
     retire
    0.45
     retired
    0.45
     inducted
    0.45
    Activations Density 0.028%

    No Known Activations