© 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. 10892
    Prev
    Next
    INDEX
    Explanations

    answer options or instructions

    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
     recognised
    1.63
     colours
    1.31
     flavours
    1.29
    いろいろ
    1.29
     learnt
    1.27
    നില്‍
    1.21
     inbuilt
    1.21
    ６
    1.20
     realised
    1.19
    ല്‍
    1.18
    POSITIVE LOGITS
     Additionally
    1.70
     המש
    1.58
     מא
    1.55
     Воз
    1.54
     Collaborative
    1.51
     Tig
    1.50
     Abschluss
    1.46
     פ
    1.45
     Tennessee
    1.44
     Isso
    1.43
    Activations Density 0.006%

    No Known Activations