© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4803
    Prev
    Next
    INDEX
    Explanations

    trying new things

    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_15_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
     standstill
    0.81
    registrer
    0.78
    actives
    0.77
     yad
    0.73
     attributing
    0.72
    akati
    0.72
    Trac
    0.72
    篤
    0.72
     datas
    0.71
     savait
    0.70
    POSITIVE LOGITS
     실패
    1.63
     Elsewhere
    1.55
     APPE
    1.49
     prue
    1.48
     Peterborough
    1.47
     Costello
    1.47
    失敗
    1.46
    lems
    1.45
    嘗試
    1.44
     različ
    1.44
    Activations Density 0.092%

    No Known Activations