© 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. 233548
    Prev
    Next
    INDEX
    Explanations

    authority assigned, Tool Kit

    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
     MANAG
    0.49
    eya
    0.47
    urias
    0.47
    rk
    0.46
    tuning
    0.45
    rivi
    0.45
    |}{
    0.44
    anci
    0.44
    nR
    0.43
    ipot
    0.43
    POSITIVE LOGITS
     অঞ্চলে
    0.52
    哒
    0.52
     Niveau
    0.51
    지역
    0.50
    地域
    0.48
     regionale
    0.48
     gewüns
    0.48
    ᾶ
    0.47
     regionales
    0.47
    区域
    0.47
    Activations Density 0.000%

    No Known Activations