© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8471
    Prev
    Next
    INDEX
    Explanations

    display current price

    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
     namens
    0.92
     मटेरियल
    0.88
    developer
    0.88
    犁
    0.86
     سخت
    0.84
    asikan
    0.84
    irty
    0.82
    തന്ത്ര
    0.81
    letter
    0.81
    spar
    0.81
    POSITIVE LOGITS
     mutation
    1.00
     ă
    1.00
     வந்த
    0.98
     ஆல
    0.97
    ጃ
    0.96
     ра
    0.93
     нама
    0.92
    왔
    0.90
     تم
    0.90
    PostMapping
    0.90
    Activations Density 0.000%

    No Known Activations