© 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. 44221
    Prev
    Next
    INDEX
    Explanations

    down the road/street/hall

    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
     EVEN
    -1.45
     ボール
    -1.41
     prouver
    -1.37
    缡
    -1.37
    foglio
    -1.34
    鶫
    -1.34
     мои
    -1.33
     maakt
    -1.33
     remettre
    -1.33
     gouttes
    -1.32
    POSITIVE LOGITS
     through
    1.68
    垻
    1.57
    ğum
    1.57
    接着
    1.46
     indicating
    1.46
     similaires
    1.43
     larga
    1.34
    camiseta
    1.34
     using
    1.33
     используя
    1.33
    Activations Density 0.012%

    No Known Activations