© 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. 7736
    Prev
    Next
    INDEX
    Explanations

    numpy random seed

    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
    اا
    2.29
    t
    2.21
    ्ह
    2.15
     commut
    2.03
    ا
    2.02
    tedir
    1.98
    ੀ
    1.97
    ्ज
    1.96
    𝗻
    1.95
    ا۔
    1.94
    POSITIVE LOGITS
     m
    1.90
    </img>
    1.80
    consin
    1.80
    ichlet
    1.79
    Bz
    1.78
    𝑚
    1.74
    പ്പെടെ
    1.74
     Mhm
    1.70
    ما
    1.68
    ings
    1.68
    Activations Density 0.000%

    No Known Activations