© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60202
    Prev
    Next
    INDEX
    Explanations

    Clint Eastwood

    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
    ’
    -2.44
    峮
    -2.36
    呖
    -2.28
     pero
    -2.28
    larda
    -2.09
    ↵↵
    -2.09
    焄
    -2.09
    ↵
    -2.06
    但
    -2.05
     mutta
    -2.03
    POSITIVE LOGITS
     feiert
    2.45
    隳
    2.41
    Ꭳ
    2.41
    筇
    2.38
    蒹
    2.38
    鸶
    2.34
     anún
    2.33
    
    2.31
     pantal
    2.22
    
    2.22
    Activations Density 0.002%

    No Known Activations