© 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. 13466
    Prev
    Next
    INDEX
    Explanations

    error handling or returning None

    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
    İlk
    1.43
    Pentru
    1.37
    То
    1.36
    Sebagai
    1.34
     मोटापा
    1.33
    Ка
    1.33
    Ро
    1.32
    ﻗ
    1.31
    На
    1.31
     Hersteller
    1.29
    POSITIVE LOGITS
     clump
    1.43
     strategic
    1.27
     grassroots
    1.20
     collective
    1.19
     larger
    1.19
     bottleneck
    1.18
     corrective
    1.18
     general
    1.15
     brick
    1.14
     remedial
    1.14
    Activations Density 0.000%

    No Known Activations