© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 11467
    Prev
    Next
    INDEX
    Explanations

    software patching and management

    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_9_width_262k_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
    в
    2.93
    egger
    2.81
    izowane
    2.66
    頷
    2.66
    forma
    2.62
    ()=>{
    2.54
    که
    2.52
    :$
    2.47
     duda
    2.46
    igui
    2.41
    POSITIVE LOGITS
    cvtColor
    3.91
    -\
    3.10
     flanges
    3.06
    $)$.
    3.03
    tting
    3.02
    াফ
    2.96
    uating
    2.95
    ுள்ளனர்
    2.92
    ्ट
    2.90
    मीटर
    2.89
    Activations Density 0.011%

    No Known Activations