© 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. 70925
    Prev
    Next
    INDEX
    Explanations

    Barbara and succeeding names

    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
     With
    -2.52
    みてください
    -2.48
     This
    -2.48
    𝘞
    -2.41
    ៚
    -2.41
     belongings
    -2.30
    ?"
    -2.28
     However
    -2.25
     escuchadas
    -2.23
    ALLENGES
    -2.23
    POSITIVE LOGITS
    .
    3.28
    providedIn
    2.81
    )\
    2.72
    ){
    2.55
    )-
    2.48
    子を
    2.48
    </h3>
    2.47
     '-')
    2.33
    ”;
    2.28
     the
    2.25
    Activations Density 0.004%

    No Known Activations