© 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. 106862
    Prev
    Next
    INDEX
    Explanations

    language names

    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
     like
    -0.85
     very
    -0.85
     and
    -0.84
     didn
    -0.79
    佼
    -0.75
     received
    -0.75
    南部
    -0.74
    主演
    -0.73
    encana
    -0.73
     becomes
    -0.72
    POSITIVE LOGITS
     konflik
    1.09
     ferie
    1.04
     ferien
    1.03
     papir
    0.98
     kaž
    0.96
     karton
    0.96
    GroupLayout
    0.96
     nede
    0.96
     eksper
    0.95
     nastro
    0.94
    Activations Density 0.006%

    No Known Activations