© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1672
    Prev
    Next
    INDEX
    Explanations

    Park Güell or similar

    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
     classico
    0.84
    Ê
    0.82
     Каждый
    0.81
     lindo
    0.80
     இருந்த
    0.79
     cơ
    0.79
     Акысыз
    0.78
    Щ
    0.76
    что
    0.75
     همه
    0.75
    POSITIVE LOGITS
     aquesta
    1.33
     perquè
    1.31
     després
    1.31
     aquest
    1.27
     també
    1.23
     dels
    1.23
     encara
    1.23
     treball
    1.22
    ència
    1.21
     està
    1.19
    Activations Density 0.032%

    No Known Activations