© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23639
    Prev
    Next
    INDEX
    Explanations

    denials of wrongdoing

    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
     famoso
    -0.93
    tando
    -0.87
    磡
    -0.84
    って
    -0.83
    nsk
    -0.83
    Failure
    -0.82
     потенциаль
    -0.81
    مه
    -0.81
    Famous
    -0.81
    岁的
    -0.80
    POSITIVE LOGITS
     allegations
    1.76
     untrue
    1.71
    false
    1.68
     false
    1.68
     misinformation
    1.67
     unfounded
    1.66
     insinu
    1.53
     allegation
    1.48
     assertions
    1.48
     slander
    1.48
    Activations Density 0.048%

    No Known Activations