© 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. 114675
    Prev
    Next
    INDEX
    Explanations

    sailing, masters, takes, receive, customers

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

    sulforaphane and cauliflower

    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
    enberg
    0.45
     Kipp
    0.43
    ล
    0.43
    uchsia
    0.42
    levance
    0.41
     చివరి
    0.40
     దూర
    0.40
    )=
    0.39
    rach
    0.39
     Constituency
    0.39
    POSITIVE LOGITS
    klı
    0.54
     coleg
    0.52
     kró
    0.50
     králov
    0.50
     korean
    0.50
     resTmp
    0.49
    ır
    0.49
    膠
    0.48
     generates
    0.47
     inverso
    0.47
    Activations Density 0.001%

    No Known Activations