© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181138
    Prev
    Next
    INDEX
    Explanations

    prevent bacterial growth

    np_acts-logits-general · gemini-2.5-flash-lite

    affine arithmetic, interval arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    aus
    0.54
     T
    0.53
    g
    0.52
    wig
    0.50
    ával
    0.50
     v
    0.49
     eux
    0.49
     O
    0.48
    ker
    0.48
    assen
    0.48
    POSITIVE LOGITS
    StatusCodes
    0.57
    ৬০
    0.52
    ቖ
    0.51
    󰡔
    0.51
    ᱔
    0.48
     seguenti
    0.47
     trasferimento
    0.47
    যত
    0.47
    ዔ
    0.47
    ？](
    0.47
    Activations Density 0.000%

    No Known Activations