© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2845
    Prev
    Next
    INDEX
    Explanations

    fish or other

    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_65k_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
    ワー
    1.13
    で行
    1.10
     話
    1.10
    ره
    1.08
     Couldn
    1.06
     asked
    1.05
    这时候
    1.04
     Turned
    1.04
     Explained
    1.03
     कार
    1.03
    POSITIVE LOGITS
     những
    1.95
    នូវ
    1.92
     aquilo
    1.81
     what
    1.58
    what
    1.57
     את
    1.51
     some
    1.45
     a
    1.38
     какие
    1.36
     the
    1.36
    Activations Density 0.724%

    No Known Activations