© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7321
    Prev
    Next
    INDEX
    Explanations

    sounds like you're experiencing

    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
     THEIR
    1.21
     WAS
    1.08
     DID
    1.04
     (
    1.00
     (“
    0.98
    😉
    0.96
    </h2>
    0.95
     HAS
    0.93
     😉
    0.93
     (*
    0.92
    POSITIVE LOGITS
     Considerations
    1.73
    ly
    1.65
    spapers
    1.59
    数据显示
    1.50
    Point
    1.49
    કો
    1.49
    Warning
    1.45
    ેચ્છ
    1.42
    icularly
    1.41
    Questions
    1.39
    Activations Density 0.827%

    No Known Activations