© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 12730
    Prev
    Next
    INDEX
    Explanations

    creative painting and art

    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
    lights
    2.37
    此同时
    2.29
    𝘻
    2.28
    𝘳
    2.27
    gien
    2.23
    erap
    2.22
     quát
    2.22
    redd
    2.20
    𝘭
    2.19
    वानिव
    2.16
    POSITIVE LOGITS
    acea
    2.43
    தமிழ்
    2.35
    년대
    2.25
    "।
    2.22
    acent
    2.21
    on
    2.19
    s
    2.16
    onate
    2.15
    '"
    2.15
    ات
    2.14
    Activations Density 0.001%

    No Known Activations