© 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. 148146
    Prev
    Next
    INDEX
    Explanations

    keywords and descriptions

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

    platonic, Immanuel Kant, Republican party

    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
     ਕਿਸ
    0.54
    lobin
    0.48
     ਜ
    0.48
    ਕਾਰ
    0.47
    autoarima
    0.47
     ਇਸ
    0.45
    樽
    0.45
     כל
    0.45
    İM
    0.45
    もあった
    0.44
    POSITIVE LOGITS
     navigated
    0.47
     Rig
    0.47
    lanır
    0.47
    ový
    0.46
     navigating
    0.46
     phù
    0.45
     Ingeniería
    0.45
    ۗ
    0.44
     Void
    0.44
     Verfahren
    0.44
    Activations Density 0.000%

    No Known Activations