© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2338
    Prev
    Next
    INDEX
    Explanations

    become state or attribute

    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_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
     estés
    2.78
    ра
    2.69
    𝑦
    2.30
    an
    2.30
    णा
    2.30
    rically
    2.29
    ⸙
    2.29
    跷
    2.27
    igree
    2.24
    BuildContext
    2.23
    POSITIVE LOGITS
    ع
    3.80
    м
    3.26
    에
    2.90
    ch
    2.85
     deci
    2.56
    ต้อง
    2.49
     delante
    2.45
    FirstResponder
    2.43
    unet
    2.43
     chắn
    2.43
    Activations Density 0.067%

    No Known Activations