© 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. 15103
    Prev
    Next
    INDEX
    Explanations

    Leveson Carmilla

    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
    ѣмъ
    -1.80
    鵟
    -1.69
    ୌ
    -1.64
     people
    -1.61
    晅
    -1.60
     good
    -1.59
    </b>
    -1.59
    ઁ
    -1.55
    ſam
    -1.53
     boneca
    -1.53
    POSITIVE LOGITS
     nyní
    1.90
     andare
    1.76
     praktische
    1.67
    3
    1.66
     Материал
    1.66
    めっちゃ
    1.56
    </h3>
    1.53
     ตาม
    1.51
    要想
    1.51
     —
    1.51
    Activations Density 0.000%

    No Known Activations