© 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. 22-GEMMASCOPE-2-RES-65K
    7. 7785
    Prev
    Next
    INDEX
    Explanations

    mineral and related resources

    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_22_width_65k_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
    рів
    0.95
     soff
    0.94
    neros
    0.93
    ഷ
    0.92
    াকে
    0.91
    embrie
    0.91
    ഇ
    0.90
     cedo
    0.89
    ່າງ
    0.88
    intentional
    0.88
    POSITIVE LOGITS
    ogical
    1.45
    ocortic
    1.26
    ogy
    0.89
    cart
    0.89
    油
    0.86
     provincia
    0.84
    numOf
    0.84
    carts
    0.83
    तों
    0.82
    a
    0.82
    Activations Density 0.019%

    No Known Activations