© 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. 22-GEMMASCOPE-RES-131K
    7. 14446
    Prev
    Next
    INDEX
    Explanations

    whether enough

    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_22/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
    textAlignment
    -0.81
     formulations
    -0.81
     elements
    -0.77
    vel
    -0.77
    whereas
    -0.75
     divisions
    -0.74
    唯有
    -0.74
    katan
    -0.73
     Donations
    -0.73
     zarówno
    -0.72
    POSITIVE LOGITS
     enough
    1.85
     suffit
    1.77
     alone
    1.74
     sufficient
    1.66
     itself
    1.52
     suffices
    1.48
    Enough
    1.48
     suficiente
    1.43
     Enough
    1.40
     yeterli
    1.38
    Activations Density 0.060%

    No Known Activations