© 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. 33097
    Prev
    Next
    INDEX
    Explanations

    sufficiently high

    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
     बहुत
    -0.82
    χύ
    -0.80
     rất
    -0.79
    읗
    -0.79
    USTER
    -0.78
    extremely
    -0.77
    (?
    -0.77
     efec
    -0.76
    albeit
    -0.76
     très
    -0.75
    POSITIVE LOGITS
     sufficiently
    3.13
     enough
    2.91
     sufficient
    2.55
     suffisamment
    2.52
     suficientemente
    2.38
    sufficient
    2.36
     Enough
    2.11
     Sufficient
    2.09
     đủ
    2.06
    enough
    2.05
    Activations Density 0.148%

    No Known Activations