© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58356
    Prev
    Next
    INDEX
    Explanations

    for any purpose

    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
    CERTIFICATE
    -0.86
     Ting
    -0.84
     lựa
    -0.80
     ngũ
    -0.79
    ьаж
    -0.77
    Ting
    -0.76
    ruitt
    -0.75
    ionario
    -0.75
    فو
    -0.75
    ARRAY
    -0.73
    POSITIVE LOGITS
     purpose
    5.94
     purposes
    5.88
    purpose
    4.19
    Purpose
    4.00
    purposes
    3.95
     Purposes
    3.81
     Purpose
    3.80
    目的
    3.53
     PURPOSE
    3.44
    PURPOSE
    3.33
    Activations Density 0.116%

    No Known Activations