© 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. 34789
    Prev
    Next
    INDEX
    Explanations

    Vocabulary, language, names, origins

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

    "boys"childbuyerspeopleargv

    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
    च्युअल
    0.48
     echocardi
    0.48
    वेलकम
    0.47
    रिमेंट
    0.46
    豁
    0.46
    CR
    0.45
    ्यूज
    0.45
    يمه
    0.44
    बाईल
    0.44
     accél
    0.44
    POSITIVE LOGITS
     Vocabulary
    0.46
     તેમના
    0.45
     ভাষা
    0.42
     Veil
    0.41
    ð
    0.41
     Tatar
    0.41
                             
    0.40
     Path
    0.40
     María
    0.39
     Cleopatra
    0.39
    Activations Density 0.000%

    No Known Activations