© 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. 10995
    Prev
    Next
    INDEX
    Explanations

    combinations formula $\binom{n}{k}$

    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
     equ
    3.22
    parse
    3.10
    Fb
    3.04
    mediaDevices
    2.99
    繖
    2.98
    発生
    2.95
    Provenance
    2.90
    ʍ
    2.87
    OURCES
    2.79
     quartz
    2.79
    POSITIVE LOGITS
    ikat
    2.37
    aryana
    2.33
    iedad
    2.27
    फना
    2.27
    chte
    2.26
    iedade
    2.25
    esterol
    2.25
    uke
    2.22
    碰
    2.21
     취
    2.14
    Activations Density 0.005%

    No Known Activations