© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3240
    Prev
    Next
    INDEX
    Explanations

    yaml selector configuration

    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
    .
    2.29
     was
    2.18
     in
    2.11
     is
    2.01
    ,
    1.97
     have
    1.95
     and
    1.85
     has
    1.84
     for
    1.81
     from
    1.80
    POSITIVE LOGITS
    贰章
    2.51
    Смалянчук
    2.40
     क़ुर्आन
    2.39
    𒆗
    2.37
    AppBsky
    2.37
     vyl
    2.34
    SRPCS
    2.33
    𒈩
    2.32
    𒆧
    2.31
    𒍝
    2.31
    Activations Density 0.109%

    No Known Activations