© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7592
    Prev
    Next
    INDEX
    Explanations

    specific capitalized words and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nickname
    1.33
    Enviar
    1.31
     czasie
    1.30
    Menurut
    1.24
    Huge
    1.22
    <unused538>
    1.22
    <unused512>
    1.22
    Packed
    1.20
     Když
    1.20
    <unused1846>
    1.20
    POSITIVE LOGITS
    [
    1.21
    <u>
    1.16
    i
    1.10
    <em>
    1.09
    </strong>
    1.06
    a
    1.04
    en
    1.04
    y
    1.03
    ((
    1.02
    j
    1.00
    Activations Density 0.118%

    No Known Activations