© 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. 7163
    Prev
    Next
    INDEX
    Explanations

    css pixel values

    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
    ‑
    1.37
    —
    1.32
     sì
    1.26
    ‒
    1.26
     –
    1.21
    –
    1.20
     —
    1.19
     거예요
    1.18
     (!)
    1.17
    ––
    1.13
    POSITIVE LOGITS
    썻
    1.35
     उसमे
    1.34
     সাধারন
    1.23
     पुरे
    1.21
     ব্যাক্ত
    1.21
     wouldnt
    1.21
    Thats
    1.20
     wasnt
    1.19
     युवाओ
    1.18
     doesnt
    1.15
    Activations Density 0.130%

    No Known Activations