© 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. 22-GEMMASCOPE-RES-131K
    7. 25645
    Prev
    Next
    INDEX
    Explanations

    sufficient

    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
     bazı
    -0.97
     belki
    -0.96
    ках
    -0.94
    𝒆
    -0.93
     one
    -0.91
    Lebih
    -0.90
    arza
    -0.87
    Manfaat
    -0.85
     two
    -0.84
     without
    -0.84
    POSITIVE LOGITS
     enough
    1.60
    Sufficient
    1.36
     sufficiently
    1.32
     comunque
    1.29
     sufficient
    1.28
     anyway
    1.27
     suffisamment
    1.26
     Sufficient
    1.26
     plenty
    1.22
     suficiente
    1.18
    Activations Density 0.052%

    No Known Activations