© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4435
    Prev
    Next
    INDEX
    Explanations

    calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    氛
    1.74
    (([
    1.68
    bleau
    1.68
     (')
    1.67
    Peace
    1.63
     ("
    1.63
    ској
    1.62
     \%(
    1.58
     expressing
    1.58
    '][
    1.58
    POSITIVE LOGITS
     başvur
    1.20
    corsi
    1.12
    suffix
    1.11
    sciences
    1.06
    achelors
    1.02
     gonz
    1.01
    棍
    1.00
     تعدى
    1.00
    şağı
    0.98
     lng
    0.96
    Activations Density 0.003%

    No Known Activations