© 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. 99170
    Prev
    Next
    INDEX
    Explanations

    SnackNation or snacks

    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
    }$
    -2.89
    嫫
    -2.64
    廨
    -2.61
    臯
    -2.52
    
    -2.38
     ܙ
    -2.38
    轳
    -2.36
    焄
    -2.31
    もの
    -2.30
    </sub>
    -2.28
    POSITIVE LOGITS
     Когда
    2.58
    ating
    2.45
    .
    2.22
     После
    2.17
    ↵↵
    2.16
    mainAxisSize
    2.09
    регистри
    2.05
     sabid
    2.05
     '
    2.02
    虓
    2.02
    Activations Density 0.004%

    No Known Activations