© 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. 3015
    Prev
    Next
    INDEX
    Explanations

    webpages and their content

    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
    й
    3.13
    o
    2.63
    ukkah
    2.36
    er
    2.34
    attan
    2.33
    a
    2.22
    ar
    2.21
    abad
    2.19
     শুটিং
    2.15
     последова
    2.12
    POSITIVE LOGITS
    сності
    2.35
    ểm
    2.28
     élu
    2.28
    “
    2.26
    \|$
    2.24
    ᛁ
    2.23
    biotic
    2.19
    囦
    2.18
    )}{
    2.18
    ಟ್
    2.17
    Activations Density 0.178%

    No Known Activations