© 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. 11313
    Prev
    Next
    INDEX
    Explanations

    any new

    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
    na
    1.11
    te
    1.07
    siniz
    1.04
    m
    0.95
    م
    0.91
    c
    0.90
     जगहों
    0.89
    ি
    0.89
    ל
    0.85
    us
    0.85
    POSITIVE LOGITS
    不论
    0.92
     Maternal
    0.92
     polyclonal
    0.90
     Developments
    0.90
     Shipbuilding
    0.89
     Supportive
    0.89
    ा
    0.89
     каким
    0.89
     colloidal
    0.87
     Army
    0.87
    Activations Density 0.043%

    No Known Activations