© 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. 2755
    Prev
    Next
    INDEX
    Explanations

    items that stick

    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
     przedsi
    0.79
     colleague
    0.78
    入院
    0.70
     człowie
    0.69
     Arbeiten
    0.69
    茲
    0.68
    itionen
    0.66
    韜
    0.64
    事物
    0.64
    レーション
    0.62
    POSITIVE LOGITS
     converters
    2.36
     builders
    2.26
    ulators
    2.21
     generators
    2.18
     scorers
    2.17
     detectors
    2.16
     solvers
    2.15
    izers
    2.15
     creators
    2.14
    ifiers
    2.14
    Activations Density 1.180%

    No Known Activations