© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8282
    Prev
    Next
    INDEX
    Explanations

    to gracefully handle

    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_22_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
     urge
    0.93
    ތ
    0.89
    arend
    0.88
    ائي
    0.87
    PlistBuddy
    0.84
    üllt
    0.84
    äär
    0.83
    ゥ
    0.82
    ating
    0.82
    ated
    0.81
    POSITIVE LOGITS
    €˜
    1.36
    €“
    1.20
    €
    1.06
    ‚¬
    1.04
     мяс
    1.03
    chloride
    1.02
    滤
    1.01
    euros
    1.01
    €”
    1.01
    €¦
    1.00
    Activations Density 0.011%

    No Known Activations