© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 256669
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    t
    0.48
    lot
    0.45
    stvo
    0.45
    margin
    0.44
    dy
    0.44
    fstream
    0.44
    spicuous
    0.44
    bx
    0.43
    lent
    0.43
    ného
    0.42
    POSITIVE LOGITS
    ?!?
    0.48
    ProductsStore
    0.47
    撣
    0.47
     दू
    0.46
    ዛ
    0.45
     받을
    0.45
    这一切
    0.43
     диапазо
    0.43
    ?!?!
    0.43
     క్రికె
    0.43
    Activations Density 0.000%

    No Known Activations