© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64759
    Prev
    Next
    INDEX
    Explanations

    question/statement starters

    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
     skall
    -0.94
     opravdu
    -0.93
     bardzo
    -0.92
     Очень
    -0.91
     temi
    -0.90
     téléph
    -0.89
     ekos
    -0.88
     trak
    -0.88
     pourront
    -0.87
     paillettes
    -0.87
    POSITIVE LOGITS
     staffers
    0.93
    为何
    0.88
     hues
    0.84
     fle
    0.82
     woes
    0.81
     chart
    0.77
     sought
    0.77
    为啥
    0.76
     flick
    0.75
     bog
    0.75
    Activations Density 0.004%

    No Known Activations