© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13639
    Prev
    Next
    INDEX
    Explanations

    graphics rendering, design, cards

    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_7_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
    <bos>
    2.79
     Venn
    2.53
    elun
    2.51
     گا۔
    2.41
    ರ್ಭ
    2.39
    akyReLU
    2.37
     IndexPath
    2.36
    emed
    2.31
     littoral
    2.30
    気づ
    2.27
    POSITIVE LOGITS
     "$(
    2.73
    thon
    2.45
     alttext
    2.41
    ത്മ
    2.33
    σι
    2.32
    ca
    2.32
    cans
    2.28
    価
    2.26
    ça
    2.25
    cona
    2.22
    Activations Density 0.013%

    No Known Activations