© 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. 103104
    Prev
    Next
    INDEX
    Explanations

    whit names

    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
    ’:
    -2.94
    .’
    -2.56
    ?).
    -2.53
    ありますが
    -2.45
    ’.
    -2.45
    ㉖
    -2.42
     également
    -2.36
    的其他
    -2.34
     are
    -2.31
    …’
    -2.30
    POSITIVE LOGITS
    0
    2.94
     démocr
    2.81
    回来了
    2.58
    蟶
    2.56
    vertible
    2.45
    笮
    2.44
    踴
    2.36
    
    2.36
    6
    2.36
     grazia
    2.36
    Activations Density 0.002%

    No Known Activations