© 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. 131699
    Prev
    Next
    INDEX
    Explanations

    my garden

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

    "film missed"

    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
    ې
    0.46
     பயன
    0.45
    сайт
    0.44
    二维码
    0.44
     campaña
    0.43
    qrcode
    0.43
    ອ
    0.43
    开源
    0.43
    GetUser
    0.43
    រ
    0.42
    POSITIVE LOGITS
     Requirements
    0.46
    ल्टा
    0.45
     Quadrupèdes
    0.44
    ENTA
    0.42
     Fittings
    0.42
     Basically
    0.42
    '
    0.42
    QUIS
    0.40
     Decorations
    0.39
     annet
    0.39
    Activations Density 0.000%

    No Known Activations