© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2319
    Prev
    Next
    INDEX
    Explanations

    letter v and V

    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
    。【
    3.78
    。[
    3.37
    。(
    3.29
    eris
    3.28
    。）
    3.26
    。)
    3.19
    र्मु
    3.18
    ❍
    3.14
    рому
    3.13
    monium
    3.05
    POSITIVE LOGITS
    বিষ্য
    3.68
    v
    3.35
    viel
    3.01
    "
    2.89
    <bos>
    2.87
    ancouver
    2.75
     tev
    2.68
    რც
    2.64
    ölker
    2.61
    ών
    2.57
    Activations Density 1.121%

    No Known Activations