© 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. 12241
    Prev
    Next
    INDEX
    Explanations

    removes, remind, remediation, remnant

    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
    ית
    3.03
     +:+
    2.98
    bump
    2.95
    ways
    2.93
    Bump
    2.80
    た
    2.60
    ⸙
    2.51
     newLine
    2.51
    state
    2.46
    line
    2.45
    POSITIVE LOGITS
    ména
    2.74
    t
    2.72
    ीट
    2.70
    atenin
    2.68
    ി
    2.61
    emain
    2.58
    Mà
    2.54
    től
    2.51
    osterone
    2.50
    tdev
    2.39
    Activations Density 0.011%

    No Known Activations