© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2740
    Prev
    Next
    INDEX
    Explanations

    tightly held, fitted, or compressed

    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_29_width_16k_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
     арен
    0.75
     আপনাদের
    0.68
    拡大
    0.66
     shamb
    0.66
    ವುದು
    0.65
    enzel
    0.64
    unstyled
    0.63
    ঋ
    0.63
    ivables
    0.62
     dil
    0.62
    POSITIVE LOGITS
     tight
    1.70
     tightly
    1.45
    tight
    1.41
    Tight
    1.37
     tighter
    1.35
     snugly
    1.20
     Tight
    1.15
    紧
    1.14
     firmly
    1.08
     flush
    1.07
    Activations Density 0.156%

    No Known Activations