© 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-262K
    7. 12002
    Prev
    Next
    INDEX
    Explanations

    useEffect calls

    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
     else
    2.28
    на
    2.25
    ्युनिकेशन
    2.03
    ق
    1.99
    й
    1.94
    ز
    1.94
     работо
    1.85
    та
    1.80
     इतर
    1.78
     ELSE
    1.77
    POSITIVE LOGITS
    timber
    2.62
    syringe
    2.39
    𝘻
    2.24
    servicio
    2.19
    tarea
    2.11
    おり
    2.08
    enie
    2.08
    ästä
    2.07
    talet
    2.06
    tions
    2.05
    Activations Density 0.002%

    No Known Activations