© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14437
    Prev
    Next
    INDEX
    Explanations

    each fragment or object's story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    Dated
    1.24
    ero
    1.07
    కుంది
    1.04
    欠
    1.03
     అంతే
    1.02
    Too
    1.00
    ସ୍
    1.00
    ann
    1.00
     فترة
    0.99
     Back
    0.99
    POSITIVE LOGITS
     борьбы
    1.53
    談
    1.53
     oppression
    1.51
    introspection
    1.47
     精
    1.45
     ingenuity
    1.43
     thinkers
    1.43
     réflexion
    1.41
    LOADSTRING
    1.40
    ើញ
    1.38
    Activations Density 0.175%

    No Known Activations