© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104261
    Prev
    Next
    INDEX
    Explanations

    probability or possibility

    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
     $\&$
    -2.20
    ︕
    -2.11
     彼女
    -2.09
    踽
    -1.99
    饜
    -1.98
    ;?
    -1.98
    焢
    -1.91
    ()"
    -1.89
    inWeight
    -1.84
     fiabilidad
    -1.82
    POSITIVE LOGITS
    {
    2.75
    2
    2.45
    1
    1.93
     endeavor
    1.80
     We
    1.80
     to
    1.79
    4
    1.76
     endeavour
    1.74
     you
    1.72
    ਲ਼
    1.66
    Activations Density 0.024%

    No Known Activations