© 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. 11505
    Prev
    Next
    INDEX
    Explanations

    evolved from ancestors

    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
    𝒔
    1.70
     tienen
    1.53
     cannon
    1.52
     swirling
    1.50
     ि
    1.50
     tiene
    1.49
     gebruik
    1.47
     tienes
    1.46
     está
    1.45
     Иногда
    1.45
    POSITIVE LOGITS
    न
    2.08
    ן
    1.89
    weise
    1.47
    npy
    1.47
    ният
    1.47
    g
    1.40
    governmental
    1.38
    पूर्व
    1.38
    Agriculture
    1.37
    point
    1.36
    Activations Density 0.003%

    No Known Activations