© 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. 22-GEMMASCOPE-RES-131K
    7. 16329
    Prev
    Next
    INDEX
    Explanations

    trash and garbage

    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_22/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
    焄
    -3.03
    噥
    -2.56
    
    -2.55
    鹋
    -2.50
    妘
    -2.38
    嫆
    -2.30
    摃
    -2.28
    过程
    -2.27
    
    -2.23
    哢
    -2.16
    POSITIVE LOGITS
    >
    1.90
    }
    1.88
     is
    1.88
    </
    1.75
    ",
    1.69
    といふ
    1.64
    that
    1.63
    </u>
    1.63
     That
    1.58
    йо
    1.57
    Activations Density 0.018%

    No Known Activations