© 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. 159596
    Prev
    Next
    INDEX
    Explanations

    congress productions

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

    single filers, sandy loam, mirrors

    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
    веро
    0.50
    ២
    0.48
    뭡
    0.46
    для
    0.44
    यल
    0.43
    过后
    0.41
    嘏
    0.41
    чения
    0.41
    Outstanding
    0.41
    ве
    0.41
    POSITIVE LOGITS
    ホ
    0.48
     தன்ன
    0.46
     ውሃ
    0.46
     teda
    0.46
     v
    0.45
     erity
    0.45
     ホ
    0.45
    ිනි
    0.45
     pri
    0.45
     হু
    0.45
    Activations Density 0.001%

    No Known Activations