© 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. 22-GEMMASCOPE-RES-131K
    7. 67254
    Prev
    Next
    INDEX
    Explanations

    automated sorting and control

    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
     for
    -1.94
    <bos>
    -1.57
     perpetually
    -1.46
     can
    -1.34
     epitom
    -1.33
     to
    -1.30
     when
    -1.30
     may
    -1.30
     supremely
    -1.29
     before
    -1.27
    POSITIVE LOGITS
    瓛
    1.72
     ſever
    1.71
    かっこ
    1.66
     unſ
    1.63
    probably
    1.63
    亹
    1.62
     ſeveral
    1.62
     débuts
    1.61
    うわ
    1.58
     Perſ
    1.57
    Activations Density 0.008%

    No Known Activations