© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9066
    Prev
    Next
    INDEX
    Explanations

    object detection or prediction

    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
    Ба
    1.11
    ج
    1.11
    ták
    1.06
    nach
    1.05
    pte
    1.04
    rj
    1.04
    ли
    1.02
    ta
    1.02
    VAT
    1.01
    ン
    1.00
    POSITIVE LOGITS
     eruptions
    1.32
    es
    1.29
    ow
    1.22
     contrasts
    1.21
    itati
    1.18
     physiologic
    1.16
     abiotic
    1.15
     mindig
    1.14
     glaciers
    1.14
     нати
    1.12
    Activations Density 0.000%

    No Known Activations