© 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. 130429
    Prev
    Next
    INDEX
    Explanations

    global followed by noun

    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
    </h3>
    -2.70
    </strong>
    -2.53
     ocorreu
    -2.14
    翃
    -2.14
    ឵
    -2.09
    気付
    -2.05
     ocorre
    -1.99
     provavelmente
    -1.98
     baseado
    -1.98
     IBRARY
    -1.98
    POSITIVE LOGITS
    s
    2.75
    </b>
    2.38
    d
    2.08
     is
    2.05
    b
    1.98
     was
    1.96
    $
    1.95
     &
    1.90
    </h5>
    1.89
     awful
    1.81
    Activations Density 0.007%

    No Known Activations