© 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. 39402
    Prev
    Next
    INDEX
    Explanations

    arrival in

    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
    <sup>
    0.44
     プ
    0.41
    placeholder
    0.41
    名人
    0.41
    月に
    0.40
     ウィ
    0.40
    Bearer
    0.40
    繰
    0.40
    ায়
    0.40
    メント
    0.39
    POSITIVE LOGITS
    tol
    0.54
     verdade
    0.52
     tigers
    0.51
     continuidade
    0.45
     rupiah
    0.45
     ieri
    0.44
    棻
    0.44
     dimensi
    0.44
     फैशन
    0.44
     otra
    0.44
    Activations Density 23.325%

    No Known Activations