© 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. 10-GEMMASCOPE-RES-131K
    7. 99749
    Prev
    Next
    INDEX
    Explanations

    Todd Wilson

    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
    ↵↵
    -2.52
     koruyucu
    -2.19
     mencegah
    -2.14
     estabiliz
    -2.06
    ൮
    -2.05
     propriété
    -2.02
    渽
    -2.00
     "
    -1.98
     menurunkan
    -1.98
    运行
    -1.93
    POSITIVE LOGITS
     That
    2.38
    (!__
    2.33
     –
    2.33
     bambu
    2.16
     Thus
    2.14
     Instantly
    2.11
     Infir
    2.11
    ,“
    2.11
     Truly
    2.09
    </i>
    2.08
    Activations Density 0.000%

    No Known Activations