© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6055
    Prev
    Next
    INDEX
    Explanations

    content point one screen photo video data

    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
     merely
    1.26
     solely
    1.13
     universally
    1.12
     presently
    1.12
     regularity
    1.11
     immediately
    1.11
     stated
    1.09
    s
    1.09
     render
    1.08
     every
    1.07
    POSITIVE LOGITS
     piensa
    1.42
    imise
    1.41
     skú
    1.39
    custId
    1.37
     děti
    1.35
    éricos
    1.34
     authToken
    1.32
     ভাবতে
    1.32
     után
    1.31
     spôsob
    1.29
    Activations Density 0.000%

    No Known Activations