© 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. 73575
    Prev
    Next
    INDEX
    Explanations

    senior portrait

    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
     and
    -2.08
     will
    -2.02
     There
    -1.98
     After
    -1.82
     "
    -1.80
     took
    -1.80
     From
    -1.77
     showed
    -1.74
     Despite
    -1.73
     two
    -1.71
    POSITIVE LOGITS
     anhänger
    1.87
     tanken
    1.85
    躂
    1.84
     kohta
    1.82
    
    1.82
     münchen
    1.80
    </b>
    1.80
     toppen
    1.75
     reflek
    1.73
    .~\
    1.73
    Activations Density 0.000%

    No Known Activations