© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1534
    Prev
    Next
    INDEX
    Explanations

    variant, foreign words, names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    でしょうね
    -1.02
     potensi
    -0.92
     annen
    -0.91
     spesifik
    -0.91
     elek
    -0.89
     drin
    -0.87
     tyn
    -0.87
     marmor
    -0.85
     Spani
    -0.84
     balas
    -0.84
    POSITIVE LOGITS
    際は
    1.16
    rolled
    1.00
     moeili
    0.99
     Variation
    0.93
     świet
    0.91
    為に
    0.89
    様な
    0.88
    ほうがいい
    0.88
     ważne
    0.87
     gemak
    0.87
    Activations Density 0.003%

    No Known Activations