© 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. 11264
    Prev
    Next
    INDEX
    Explanations

    and

    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
     conduct
    1.22
    sız
    0.96
     neighboring
    0.93
    l
    0.92
     conductance
    0.90
    வற்றை
    0.90
     Milky
    0.89
     bertujuan
    0.88
     위한
    0.88
     Lagrangian
    0.87
    POSITIVE LOGITS
     और
    1.48
     و
    1.40
    ங்கிணை
    1.35
    และ
    1.35
     και
    1.35
     एवं
    1.29
     आणि
    1.29
     и
    1.28
     attuale
    1.28
     และ
    1.28
    Activations Density 0.237%

    No Known Activations