© 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. 11120
    Prev
    Next
    INDEX
    Explanations

    Greene, Rourke, Hydro, Pepper, wolves

    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
     Đặc
    2.22
    FEATURES
    2.21
    ΐ
    2.17
    PHIA
    2.12
    вина
    2.12
     純正
    2.11
     ObjectId
    2.11
     وهي
    2.10
     đặc
    2.08
    දය
    2.08
    POSITIVE LOGITS
    n
    2.46
    sa
    2.37
    sk
    2.35
    uit
    2.24
    si
    2.16
    utations
    2.13
    ns
    2.04
    ting
    2.00
    nk
    1.97
    summ
    1.96
    Activations Density 0.000%

    No Known Activations