© 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. 10-GEMMASCOPE-RES-131K
    4. 101573
    Prev
    Next
    INDEX
    Explanations

    file extensions and file names

    np_acts-logits-general · gemini-2.5-flash-lite

    file extensions, particularly for common document and data file formats.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    akteur
    -1.76
    
    -1.63
     approu
    -1.59
     "]";
    -1.55
    𓁹
    -1.54
    𖣔
    -1.53
     célébr
    -1.52
     sembl
    -1.49
     ”
    -1.49
    意外と
    -1.48
    POSITIVE LOGITS
     or
    2.84
     this
    2.41
     from
    2.20
     for
    2.17
     and
    2.17
     when
    2.08
    this
    2.02
     because
    1.97
     with
    1.82
    there
    1.71
    Activations Density 0.069%

    No Known Activations