© 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. 4292
    Prev
    Next
    INDEX
    Explanations

    oil or fat

    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
     AMG
    1.16
    antis
    1.08
    AMG
    1.07
    рани
    1.06
     график
    1.05
     скри
    1.04
    <0xAB>
    1.03
    Affine
    0.99
     काफ
    0.99
    กรา
    0.98
    POSITIVE LOGITS
    放入
    1.20
     سیم
    1.14
     unearthed
    1.14
     चार्
    1.13
    পরিচিত
    1.13
    shaped
    1.11
     illustrated
    1.10
     Biographical
    1.08
     आढळ
    1.07
     圆
    1.06
    Activations Density 0.188%

    No Known Activations