© 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. 44006
    Prev
    Next
    INDEX
    Explanations

    pow variant start

    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
    诹
    -2.53
    няет
    -2.47
    
    -2.45
     ,,
    -2.42
     flawed
    -2.39
    ・・・」
    -2.36
    倧
    -2.31
    .”
    -2.28
     ventanas
    -2.17
    Buongiorno
    -2.17
    POSITIVE LOGITS
    s
    2.73
    </sup>
    2.58
     If
    2.53
    很好的
    2.36
    屣
    2.33
    氿
    2.30
                
    2.27
    豋
    2.25
     Neurology
    2.22
                        
    2.19
    Activations Density 0.002%

    No Known Activations