© 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. 4351
    Prev
    Next
    INDEX
    Explanations

    engineering, time, values

    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
    בער
    1.48
     পিটার
    1.29
    ENDMENT
    1.28
     Ordinary
    1.28
    ாதி
    1.25
     মিঠ
    1.24
    앗
    1.24
    א
    1.24
     Object
    1.21
    BeginInit
    1.21
    POSITIVE LOGITS
     másik
    1.29
     più
    1.19
    lerinden
    1.18
    ciju
    1.16
    standen
    1.15
    পূর্ন
    1.14
    ervices
    1.11
    より
    1.10
    সাধন
    1.10
    kuensi
    1.09
    Activations Density 0.001%

    No Known Activations