© 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. 3740
    Prev
    Next
    INDEX
    Explanations

    mathematical code and recursion

    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
    ávy
    1.42
    نٹ
    1.38
    orter
    1.34
    achers
    1.33
     trebui
    1.31
     پلی
    1.29
    apatos
    1.28
    訶
    1.28
    ション
    1.28
    richtungen
    1.25
    POSITIVE LOGITS
     Steward
    1.55
     Zuh
    1.54
     시작
    1.51
     Grecia
    1.51
     SQLite
    1.47
     microcos
    1.47
     Hạ
    1.45
     Query
    1.42
     enumer
    1.41
     colaboradores
    1.41
    Activations Density 0.022%

    No Known Activations