© 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. 58492
    Prev
    Next
    INDEX
    Explanations

    accidental events and outcomes

    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
    didn
    -0.97
    comparable
    -0.93
    🍾
    -0.91
    槤
    -0.89
    iedenen
    -0.88
     kantor
    -0.87
    Failed
    -0.87
    conducted
    -0.86
    SCAR
    -0.85
    wavelength
    -0.85
    POSITIVE LOGITS
     or
    1.30
     happen
    1.16
     circumstances
    1.16
     but
    1.11
     melhor
    1.03
     discover
    1.02
     glance
    1.02
     happens
    1.01
     coinc
    0.99
     acquire
    0.97
    Activations Density 0.028%

    No Known Activations