© 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. 72886
    Prev
    Next
    INDEX
    Explanations

    crash and its related phrases

    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
    </h3>
    -2.92
    
    -2.80
    秝
    -2.69
    塤
    -2.66
    珢
    -2.64
    ⎆
    -2.61
    萑
    -2.56
    昻
    -2.50
     และ
    -2.45
    谖
    -2.44
    POSITIVE LOGITS
    </b>
    3.17
    i
    2.42
    ↵
    2.39
    s
    2.38
    }
    2.22
    be
    2.17
     slump
    2.13
    iapkan
    2.05
    y
    2.05
    遢
    1.98
    Activations Density 0.011%

    No Known Activations