© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123625
    Prev
    Next
    INDEX
    Explanations

    Are you questions

    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
    ]
    -3.14
    }
    -2.83
    
    -2.66
     to
    -2.56
    </h2>
    -2.50
    ፨
    -2.44
     chão
    -2.36
    饪
    -2.36
    ".
    -2.34
    s
    -2.34
    POSITIVE LOGITS
    ка
    2.97
    Other
    2.69
    The
    2.48
    There
    2.44
    </sub>
    2.31
     europea
    2.27
    For
    2.25
    閦
    2.22
    Another
    2.22
     ‘‘
    2.17
    Activations Density 0.007%

    No Known Activations