© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84657
    Prev
    Next
    INDEX
    Explanations

    of [noun/descriptor]

    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
     such
    -1.75
     of
    -1.63
    giày
    -1.60
     about
    -1.59
     oiseau
    -1.46
    
    -1.41
     ſuch
    -1.39
     a
    -1.39
     Songtext
    -1.37
    wyczaj
    -1.35
    POSITIVE LOGITS
    Their
    1.65
    Another
    1.53
    可不是
    1.41
     />
    1.40
    Which
    1.38
    They
    1.38
     –
    1.38
     reichlich
    1.38
    There
    1.38
    无数
    1.37
    Activations Density 0.095%

    No Known Activations