© 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. 234045
    Prev
    Next
    INDEX
    Explanations

    apprentice training, worldwide screening

    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
     dolore
    0.45
     -
    0.45
    PAINT
    0.45
    ROM
    0.44
     içine
    0.43
    Sequ
    0.42
    ோட
    0.42
    ]='
    0.42
    塗り
    0.42
    IOD
    0.42
    POSITIVE LOGITS
     Sections
    0.51
    শরণ
    0.49
     नवे
    0.48
    pidos
    0.48
     ప్రభుత్వ
    0.48
    భర
    0.48
     Constit
    0.46
     కొత్త
    0.46
    寶
    0.45
     Writers
    0.45
    Activations Density 0.001%

    No Known Activations