© 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. 142259
    Prev
    Next
    INDEX
    Explanations

    heat and change

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

    conventions and culture

    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
    under
    0.51
     UNDER
    0.47
     LEFT
    0.46
    orm
    0.45
    María
    0.45
     hinted
    0.44
    EUR
    0.43
    ମ
    0.43
    UDE
    0.42
    フォロー
    0.42
    POSITIVE LOGITS
     Convention
    0.54
     Conventions
    0.53
     conventions
    0.52
     convention
    0.51
    ناک
    0.50
    convention
    0.49
     โจทย์
    0.46
     Photonics
    0.46
     Literature
    0.45
     Biophys
    0.44
    Activations Density 0.000%

    No Known Activations