© 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. 182023
    Prev
    Next
    INDEX
    Explanations

    encouragement charged standard gum

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

    photography sites, climbing sites

    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
    陘
    0.52
     alkoh
    0.46
    cares
    0.46
    欣賞
    0.46
    頃
    0.45
    dus
    0.44
    cana
    0.44
    上に
    0.44
    ナ
    0.44
    lij
    0.43
    POSITIVE LOGITS
     onscreen
    0.52
    خذ
    0.49
     wei
    0.46
     demod
    0.45
     stated
    0.45
     rendered
    0.45
    也不能
    0.45
     Lehrer
    0.44
     wenden
    0.43
     then
    0.43
    Activations Density 0.000%

    No Known Activations