© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11765
    Prev
    Next
    INDEX
    Explanations

    noticed you

    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
    た
    2.99
    ة
    2.68
    ঙালি
    2.57
    ுகளை
    2.55
    ిన
    2.49
    ფილი
    2.47
    সে
    2.44
    capt
    2.36
    MINE
    2.34
    штар
    2.34
    POSITIVE LOGITS
    র
    3.26
    s
    3.15
    愎
    3.06
    ম
    2.90
    AnimationFrame
    2.88
    rn
    2.88
    علي
    2.85
    न
    2.85
    費
    2.81
    tale
    2.79
    Activations Density 0.026%

    No Known Activations