© 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. 110555
    Prev
    Next
    INDEX
    Explanations

    names ending in smith

    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
     âme
    -2.36
    ۔
    -2.17
     andere
    -2.14
     secretive
    -2.08
     otras
    -2.08
     sculpted
    -2.06
     replete
    -2.06
    on
    -2.03
    鲀
    -2.02
    </em>
    -1.99
    POSITIVE LOGITS
    s
    2.97
                
    2.38
     pueden
    2.30
    I
    2.13
     creando
    2.11
     This
    2.09
     generando
    2.08
     respondeu
    2.06
     explicou
    2.03
    Ⅲ
    2.02
    Activations Density 0.004%

    No Known Activations