© 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. 3161
    Prev
    Next
    INDEX
    Explanations

    code comments and disclaimers

    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
    ângulo
    2.68
    ு
    2.66
     patrón
    2.58
    erode
    2.57
    府県
    2.55
    uintes
    2.50
    椏
    2.45
    валі
    2.43
    popupTheme
    2.42
     PopupWindow
    2.40
    POSITIVE LOGITS
    ldi
    2.41
    itoria
    2.37
    ("["
    2.35
    tting
    2.35
     exchanger
    2.34
     rt
    2.33
     обмен
    2.30
     exchange
    2.30
    忱
    2.28
    पद
    2.28
    Activations Density 0.200%

    No Known Activations