© 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. 12136
    Prev
    Next
    INDEX
    Explanations

    diet plan, folds down, factual QA

    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
    馳
    1.52
    驰
    1.51
    BUFFER
    1.49
    驮
    1.48
    脖
    1.48
    acto
    1.48
    θη
    1.45
     screamed
    1.45
    繹
    1.44
     dreamed
    1.44
    POSITIVE LOGITS
     glaz
    1.39
     Hasil
    1.38
    dez
    1.33
     während
    1.33
     geng
    1.30
    ografi
    1.24
    erna
    1.22
     Isol
    1.22
     und
    1.22
    atis
    1.22
    Activations Density 0.000%

    No Known Activations