© 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. 32228
    Prev
    Next
    INDEX
    Explanations

    negated statements of absence

    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
     faktiskt
    -0.89
    Mappings
    -0.84
    ⍨
    -0.82
    もった
    -0.80
    BOTH
    -0.80
     極
    -0.79
    །
    -0.79
    Partly
    -0.79
    Wirk
    -0.77
     baada
    -0.77
    POSITIVE LOGITS
     pana
    1.02
     silver
    1.00
     currently
    0.93
    Shy
    0.92
     secret
    0.92
     Polly
    0.91
     solved
    0.91
    vidence
    0.91
    silver
    0.87
    omsday
    0.85
    Activations Density 0.040%

    No Known Activations