© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5967
    Prev
    Next
    INDEX
    Explanations

    ways to present options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    辿
    1.52
     découvert
    1.49
    incer
    1.47
     koll
    1.43
    Clean
    1.38
     dày
    1.38
    isodes
    1.35
     mulut
    1.35
    ixar
    1.35
     setiap
    1.34
    POSITIVE LOGITS
    mia
    2.23
     undetermined
    2.01
    mals
    2.01
    ᐊ
    1.96
    ortion
    1.94
    nią
    1.93
    なわち
    1.92
    archical
    1.92
    일부터
    1.91
     autre
    1.91
    Activations Density 0.019%

    No Known Activations