© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2611
    Prev
    Next
    INDEX
    Explanations

    planning and research activities

    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
     상승
    1.32
    σης
    1.11
     위해서
    1.10
     천
    1.10
     (~
    1.08
    蠻
    1.08
     왼쪽
    1.07
    렙
    1.07
     구간
    1.05
    在一起
    1.05
    POSITIVE LOGITS
     Dris
    1.40
    dll
    1.37
     Crac
    1.36
    etc
    1.35
     aud
    1.35
     sonido
    1.31
     Bohemia
    1.31
     dll
    1.30
     Jér
    1.28
     Gus
    1.28
    Activations Density 0.324%

    No Known Activations