© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13617
    Prev
    Next
    INDEX
    Explanations

    the number 99

    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_22/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
    に行って
    -2.48
     bytu
    -2.41
    に行く
    -2.05
    を作って
    -2.05
     zosta
    -2.03
    に行った
    -1.98
     kontaktu
    -1.96
    corrhi
    -1.94
    に行きました
    -1.93
     saben
    -1.92
    POSITIVE LOGITS
    that
    2.64
    —
    2.52
    m
    2.33
    g
    2.23
    }
    2.22
    l
    2.09
    を
    2.06
     что
    2.02
    i
    1.98
    y
    1.96
    Activations Density 0.023%

    No Known Activations