© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10960
    Prev
    Next
    INDEX
    Explanations

    compact, closed, connected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cerebrospinal
    2.02
    𝐊
    1.65
    𝐗
    1.64
    𝐑
    1.61
    𝙀
    1.59
     alors
    1.58
     mating
    1.57
     impro
    1.57
     effectu
    1.57
    <unused20>
    1.56
    POSITIVE LOGITS
    ie
    1.93
    as
    1.69
    ness
    1.68
    ون
    1.68
    side
    1.62
    i
    1.60
    स
    1.54
    ν
    1.49
    ted
    1.46
    х
    1.43
    Activations Density 0.002%

    No Known Activations