© 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. 11181
    Prev
    Next
    INDEX
    Explanations

    Facebook Groups

    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
    𝐰
    2.01
    𝐤
    1.87
    𝐜
    1.80
    𝐫
    1.79
    𝐯
    1.74
    𝐮
    1.73
     sort
    1.72
    𝐠
    1.71
    𝐧
    1.71
    𝐦
    1.69
    POSITIVE LOGITS
    tive
    1.85
    ש
    1.79
    s
    1.71
    holen
    1.69
    ҳ
    1.66
     shortening
    1.64
    schlag
    1.59
    zeuge
    1.58
    ה
    1.57
    schild
    1.57
    Activations Density 0.020%

    No Known Activations