© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13012
    Prev
    Next
    INDEX
    Explanations

    documentation provided with distribution

    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
     with
    -2.00
     at
    -1.81
     if
    -1.77
     Providing
    -1.73
     in
    -1.73
     for
    -1.65
     because
    -1.63
     Those
    -1.61
     on
    -1.60
     Knowing
    -1.58
    POSITIVE LOGITS
    菒
    1.91
    鲞
    1.77
     insanely
    1.68
    耵
    1.53
     semelh
    1.52
    坶
    1.52
     gigantic
    1.51
    釭
    1.51
    甞
    1.48
    )
    1.45
    Activations Density 0.024%

    No Known Activations