© 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. 10-GEMMASCOPE-RES-131K
    7. 61287
    Prev
    Next
    INDEX
    Explanations

    Forwarded

    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_10/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
    føring
    -1.64
    夘
    -1.63
     OTHER
    -1.60
    ⍢
    -1.59
    ఁ
    -1.58
    躂
    -1.50
     calientes
    -1.49
    LECTIONS
    -1.48
    ască
    -1.47
    mengen
    -1.45
    POSITIVE LOGITS
     to
    1.86
     for
    1.53
     since
    1.40
     by
    1.38
     They
    1.37
     into
    1.36
    Which
    1.33
     Since
    1.33
     Assuming
    1.30
     we
    1.25
    Activations Density 0.071%

    No Known Activations