© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11114
    Prev
    Next
    INDEX
    Explanations

    control ID

    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_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
    cklen
    1.27
     Middle
    1.15
    ántica
    1.15
    StatusCodes
    1.14
    傗
    1.12
    ッドレス
    1.09
    नॉ
    1.08
    <0xD3>
    1.08
    Middle
    1.06
    পদার্থ
    1.06
    POSITIVE LOGITS
     dai
    0.89
     okolo
    0.72
     it
    0.70
     dadurch
    0.69
     som
    0.68
     tableView
    0.68
     checkbox
    0.68
     ark
    0.65
     fumble
    0.64
     mv
    0.64
    Activations Density 0.004%

    No Known Activations