© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6917
    Prev
    Next
    INDEX
    Explanations

    concepts of time and space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arete
    1.44
    onents
    1.40
    ERI
    1.33
    witz
    1.31
    uminum
    1.29
    リューム
    1.29
     resultlist
    1.24
    腩
    1.22
     rén
    1.22
    istas
    1.22
    POSITIVE LOGITS
     circumstances
    1.73
     Finite
    1.62
     beck
    1.60
     сказа
    1.59
     seeding
    1.56
     finite
    1.56
     circumstance
    1.56
     spinner
    1.55
     presents
    1.55
    有限
    1.55
    Activations Density 0.310%

    No Known Activations