© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14911
    Prev
    Next
    INDEX
    Explanations

    However, signals a structured explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    ន្ត
    1.05
     somatic
    1.04
     자주
    1.02
     oscillations
    0.97
    iosis
    0.92
    వృద్ధి
    0.92
    통산
    0.92
    ﻂ
    0.92
     mortality
    0.91
     tangents
    0.90
    POSITIVE LOGITS
     Beek
    1.11
    Está
    1.05
     está
    1.03
     paž
    1.02
     unfolded
    1.02
     Está
    1.01
     comenzó
    0.99
     کول
    0.99
     empez
    0.99
     comenz
    0.98
    Activations Density 0.153%

    No Known Activations