© 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. 34-GEMMASCOPE-RES-131K
    7. 4320
    Prev
    Next
    INDEX
    Explanations

    in other words

    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
     चाहता
    -0.75
    ǧ
    -0.75
    缝
    -0.75
     PHILIP
    -0.73
    toit
    -0.70
    CADE
    -0.70
    𝒍
    -0.68
    แป
    -0.68
    mande
    -0.66
     esquí
    -0.66
    POSITIVE LOGITS
     words
    7.25
    words
    5.09
    Words
    4.88
     Words
    4.75
     palabras
    4.13
     WORDS
    3.86
    WORDS
    3.66
     palavras
    3.52
     слова
    3.38
     woorden
    3.19
    Activations Density 0.027%

    No Known Activations