© 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. 56062
    Prev
    Next
    INDEX
    Explanations

    introduced books

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

    career trajectories

    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
    гля
    0.52
    с
    0.50
    ଙ
    0.48
    (
    0.47
    у
    0.46
    iffin
    0.45
    риа
    0.45
    н
    0.45
    hey
    0.44
    izare
    0.44
    POSITIVE LOGITS
    導致
    0.47
     Aquatic
    0.46
     Quartet
    0.45
     করেছিল
    0.44
     Keychain
    0.44
     Wines
    0.43
     নিপী
    0.43
     Geological
    0.42
     الطبي
    0.42
     時間
    0.42
    Activations Density 0.000%

    No Known Activations