© 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. 14907
    Prev
    Next
    INDEX
    Explanations

    Okay, new

    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
    ș
    1.09
    UX
    1.06
    Ș
    1.03
     $\
    0.99
    ț
    0.96
    első
    0.95
     Treasures
    0.93
     Wied
    0.91
     Ș
    0.91
     العد
    0.90
    POSITIVE LOGITS
    igr
    1.52
    +](=
    1.48
     "*************
    1.43
     "*************"
    1.42
    ipos
    1.39
    maligngroup
    1.37
    <unused739>
    1.36
    MktCap
    1.36
    pgamma
    1.34
    评分
    1.34
    Activations Density 0.000%

    No Known Activations