© 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. 14337
    Prev
    Next
    INDEX
    Explanations

    connection, systems, and progress

    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
    íte
    1.54
     रो
    1.44
    𝚝
    1.37
    cds
    1.35
     شركة
    1.34
    Dro
    1.33
     رسمي
    1.32
    hu
    1.32
    𝚌
    1.31
    Complete
    1.31
    POSITIVE LOGITS
     coincident
    1.26
    튿
    1.09
     marginal
    1.03
     Nunn
    1.02
    삽
    1.02
     concurs
    1.01
     Tuesdays
    1.01
     Thursdays
    1.00
    жень
    1.00
     далее
    0.99
    Activations Density 0.000%

    No Known Activations