© 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. 86297
    Prev
    Next
    INDEX
    Explanations

    Chinese names

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

    document processing, AI, spies

    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
     Gretchen
    0.35
     {,
    0.32
     Trees
    0.32
     {
    0.32
     其
    0.32
    ος
    0.32
     Sally
    0.32
     Conservancy
    0.32
    issanti
    0.32
    anking
    0.31
    POSITIVE LOGITS
     blatantly
    0.36
    과
    0.33
    Preface
    0.31
    ஃப
    0.31
     वाप
    0.31
    NOM
    0.31
    MY
    0.30
    ও
    0.30
    Chat
    0.30
    MT
    0.30
    Activations Density 0.000%

    No Known Activations