© 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. 49422
    Prev
    Next
    INDEX
    Explanations

    double checking or verifying

    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
     включа
    -0.98
     Stru
    -0.79
    verläs
    -0.79
    それにしても
    -0.79
    matory
    -0.79
     GridLayout
    -0.74
     slaugh
    -0.74
    名前
    -0.73
    )}_{
    -0.73
     Bite
    -0.73
    POSITIVE LOGITS
     double
    1.72
    double
    1.59
    Double
    1.42
     Double
    1.28
    DOUBLE
    1.27
     triple
    1.27
     DOUBLE
    1.22
    triple
    1.13
     doble
    1.09
     雙
    1.09
    Activations Density 0.018%

    No Known Activations