© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 994
    Prev
    Next
    INDEX
    Explanations

    Handling invalid input errors

    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_65k_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
     ekonomik
    0.94
    ϱ
    0.94
     moderate
    0.93
     mathematical
    0.90
     thc
    0.90
    ᴋ
    0.89
     openness
    0.88
     unethical
    0.87
    𝗍
    0.87
     calculators
    0.86
    POSITIVE LOGITS
    .
    1.08
    ↵↵
    1.03
    ;
    0.97
    ,
    0.96
     ที่
    0.95
     для
    0.94
    ..
    0.94
     که
    0.94
     (
    0.90
     за
    0.89
    Activations Density 0.025%

    No Known Activations