© 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. 2345
    Prev
    Next
    INDEX
    Explanations

    seconds

    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
     emer
    0.65
     स्थापित
    0.65
    рё
    0.65
     स्पी
    0.64
    iegel
    0.64
    ൃ
    0.63
     KUM
    0.62
    MGMT
    0.62
     અવ
    0.62
    <unused2132>
    0.62
    POSITIVE LOGITS
     seconds
    3.80
     second
    3.33
    seconds
    3.33
    second
    3.25
     segundos
    3.24
     Seconds
    3.18
     secondi
    3.13
     secondes
    3.13
    秒
    3.10
    Second
    3.06
    Activations Density 0.480%

    No Known Activations