© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56860
    Prev
    Next
    INDEX
    Explanations

    following specific 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
    Negative Logits
    ousel
    -0.88
     camiones
    -0.85
    tits
    -0.84
     ANSWER
    -0.81
    kými
    -0.80
    づけ
    -0.79
    untergang
    -0.79
    ReactDOM
    -0.78
    髖
    -0.77
    Ḏ
    -0.77
    POSITIVE LOGITS
     *_
    0.93
    runde
    0.90
    tischen
    0.84
     mixta
    0.80
    inius
    0.79
    meg
    0.78
    其實
    0.78
    atalos
    0.77
    localObject
    0.77
    سين
    0.76
    Activations Density 0.003%

    No Known Activations