© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180988
    Prev
    Next
    INDEX
    Explanations

    Pate, session, Lenovo

    np_acts-logits-general · gemini-2.5-flash-lite

    figurine of an alien

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ToGo
    0.49
    ༢
    0.49
    🏞
    0.46
    𝗙
    0.44
    <0x94>
    0.44
    ใ
    0.44
    的东西
    0.43
    が無い
    0.43
    诓
    0.43
    🩺
    0.43
    POSITIVE LOGITS
     the
    0.57
    0.53
     B
    0.53
     Kat
    0.51
     Mali
    0.48
     moim
    0.47
     Kir
    0.47
     D
    0.46
     his
    0.46
     T
    0.46
    Activations Density 0.011%

    No Known Activations