© 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. 106307
    Prev
    Next
    INDEX
    Explanations

    shell variables and command substitution

    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
     ouverts
    -0.81
     vertelt
    -0.78
     micrófono
    -0.78
    zetten
    -0.78
    (_)
    -0.77
     muziek
    -0.77
    _'+
    -0.76
    ﻛ
    -0.76
     consegui
    -0.76
    Dimensi
    -0.76
    POSITIVE LOGITS
     Anato
    0.89
    _
    0.83
    halter
    0.81
    </td>
    0.81
    电梯
    0.81
    ்த
    0.79
     YA
    0.79
     Ven
    0.78
    なあ
    0.77
     ppm
    0.76
    Activations Density 0.026%

    No Known Activations