© 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. 57238
    Prev
    Next
    INDEX
    Explanations

    done good things, invading, pets, markup

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

    akin to

    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
    2
    0.50
    together
    0.41
    沉积
    0.41
     specific
    0.40
     depressive
    0.40
     art
    0.39
    1
    0.39
    specific
    0.39
     browser
    0.38
     serem
    0.38
    POSITIVE LOGITS
    SanPham
    0.44
    Datei
    0.43
     компью
    0.43
     situaciones
    0.42
     Nexon
    0.41
    kaar
    0.41
     ازاي
    0.41
     survived
    0.41
    픔
    0.40
     Realt
    0.40
    Activations Density 0.000%

    No Known Activations