© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69469
    Prev
    Next
    INDEX
    Explanations

    javascript code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    griffen
    1.26
    azir
    1.25
    oczy
    1.19
     الاق
    1.18
     sakta
    1.15
     Relations
    1.14
     sakte
    1.12
    <0x9A>
    1.12
    smanship
    1.11
    ologa
    1.10
    POSITIVE LOGITS
    UEFA
    1.30
     Knesset
    1.30
    FIFA
    1.29
     FIFA
    1.27
    Stadium
    1.25
    '))
    1.25
     Flughafen
    1.24
     stadium
    1.22
     UEFA
    1.22
    Prefab
    1.19
    Activations Density 0.002%

    No Known Activations