© 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. 22-GEMMASCOPE-RES-131K
    7. 15159
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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_22/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
    HtmlAttribute
    -1.07
    mmer
    -0.91
     از
    -0.91
    !
    -0.89
    })()
    -0.88
    分钟
    -0.86
     Ekim
    -0.85
    //$
    -0.85
    といった
    -0.84
    फ़
    -0.84
    POSITIVE LOGITS
     særlig
    1.00
     Somebody
    0.99
     lumea
    0.98
     nivelul
    0.97
     sonno
    0.94
     în
    0.94
     eventId
    0.94
     batteria
    0.93
    Takk
    0.92
     لازم
    0.91
    Activations Density 0.028%

    No Known Activations