© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 88
    Prev
    Next
    INDEX
    Explanations

    pero recomendado, porque es

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     Э
    0.60
     Ин
    0.57
    Э
    0.57
     Các
    0.56
     การ
    0.56
     Vý
    0.56
     Ј
    0.55
     Диа
    0.54
     Па
    0.53
     إ
    0.53
    POSITIVE LOGITS
     se
    0.47
     prend
    0.31
     dando
    0.29
     assum
    0.29
     é
    0.29
     discut
    0.28
     resta
    0.28
     interrom
    0.27
     consegu
    0.27
     pensando
    0.26
    Activations Density 0.067%

    No Known Activations