© 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. 7585
    Prev
    Next
    INDEX
    Explanations

    north or south side

    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
     
    -2.69
    躂
    -2.48
    垕
    -2.25
    イイ
    -2.09
    ⃢
    -2.08
    辚
    -2.08
    かっこ
    -2.06
    葑
    -2.05
    im
    -2.03
    勦
    -2.03
    POSITIVE LOGITS
     are
    2.91
    鯓
    2.88
     will
    2.64
    。　　
    2.58
    s
    2.56
     east
    2.53
    鹇
    2.50
    桖
    2.39
    🛖
    2.38
    攫
    2.36
    Activations Density 0.018%

    No Known Activations