© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10381
    Prev
    Next
    INDEX
    Explanations

    direction analysis

    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
    ">)</
    1.19
    ط
    1.18
    e
    1.11
    ット
    1.11
     deren
    1.11
    ️⃣
    1.09
    cstdlib
    1.09
    त
    1.08
    ele
    1.06
     rodzaj
    1.06
    POSITIVE LOGITS
     artistique
    1.60
    ichlet
    1.52
     acycl
    1.44
     cosines
    1.35
    snd
    1.27
    RAEL
    1.24
    導數
    1.21
     Nxg
    1.19
    বর্ধমান
    1.17
    ksen
    1.13
    Activations Density 0.137%

    No Known Activations