© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2374
    Prev
    Next
    INDEX
    Explanations

    command-line options and flags

    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_15_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
     minimising
    2.03
    더라구요
    1.92
     minimise
    1.89
     maximising
    1.77
     &,
    1.74
     &
    1.74
    ”,
    1.73
     maximise
    1.71
     optimise
    1.66
    )”.
    1.64
    POSITIVE LOGITS
     --
    1.99
    --
    1.97
    ---
    1.96
    --,
    1.94
    -----
    1.91
    !--
    1.91
    ，
    1.84
     ---
    1.82
    .--
    1.81
    -----------
    1.80
    Activations Density 0.092%

    No Known Activations