© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127789
    Prev
    Next
    INDEX
    Explanations

    programming code blocks

    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
     it
    -1.58
     when
    -1.56
    一の
    -1.48
     not
    -1.44
    
    -1.42
    珖
    -1.42
     without
    -1.37
     a
    -1.34
    isesi
    -1.31
     caminhão
    -1.30
    POSITIVE LOGITS
    ]
    1.52
     honom
    1.51
     "}";
    1.48
    }>{
    1.46
    と同じ
    1.45
    チョイス
    1.41
    *
    1.41
     последних
    1.39
    Your
    1.38
     ihn
    1.34
    Activations Density 0.025%

    No Known Activations