© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1820
    Prev
    Next
    INDEX
    Explanations

    code error handling

    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
    s
    1.25
    quia
    1.22
    nz
    1.18
    silk
    1.18
    mc
    1.17
    op
    1.15
    CP
    1.15
    wood
    1.14
    izz
    1.13
    SS
    1.12
    POSITIVE LOGITS
    ｩ
    1.30
    ਢ
    1.22
     škola
    1.21
    롤
    1.19
     loadAnimation
    1.16
     pâ
    1.16
     rám
    1.16
     htt
    1.15
    勧
    1.12
     Schema
    1.12
    Activations Density 0.001%

    No Known Activations