© 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. 11367
    Prev
    Next
    INDEX
    Explanations

    HTML closing elements

    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
    慮
    2.34
     trunk
    2.28
    తులు
    2.18
    imeters
    2.13
     microns
    2.09
    Wires
    2.08
    ㈣
    2.04
    い
    2.04
     trunks
    2.02
    ênt
    2.02
    POSITIVE LOGITS
    𝘭
    2.60
    ᆨ
    2.57
    𝘴
    2.56
    𝘪
    2.51
    ᄐ
    2.49
    𝘳
    2.42
    𝘨
    2.36
    𝘯
    2.35
    ᄑ
    2.33
    𝘰
    2.33
    Activations Density 0.021%

    No Known Activations