© 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. 101158
    Prev
    Next
    INDEX
    Explanations

    sending information and messages

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

    explains effects, styles, layers, sessions

    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
     respectable
    0.48
    ኮ
    0.46
    Benzoimidazol
    0.46
     pajama
    0.43
    verg
    0.42
    Maryam
    0.41
     deformity
    0.41
    веду
    0.40
    鱉
    0.40
    pector
    0.40
    POSITIVE LOGITS
     arranges
    0.48
    ویت
    0.46
     Signs
    0.44
     Surrounded
    0.44
     substrates
    0.43
     using
    0.42
     Remains
    0.42
     xử
    0.42
     Pflanzen
    0.42
    溲
    0.41
    Activations Density 0.000%

    No Known Activations