© 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. 10378
    Prev
    Next
    INDEX
    Explanations

    weights model

    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
    एँ
    2.33
    ઈ
    2.22
    סט
    2.21
    ED
    2.17
    एं
    2.16
    𝘢
    2.15
    𝘳
    2.08
     juice
    2.07
    то
    2.06
    𝘴
    2.06
    POSITIVE LOGITS
    heets
    4.34
    olutions
    4.05
    heet
    4.04
    ervices
    3.94
    chool
    3.86
    uggest
    3.72
    mith
    3.70
    ymbol
    3.62
    creen
    3.61
    hift
    3.59
    Activations Density 1.281%

    No Known Activations