© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129187
    Prev
    Next
    INDEX
    Explanations

    sentence start detection

    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
    ]=='
    -0.99
    ]!='
    -0.96
    ))){
    -0.95
     vẫn
    -0.93
    <>
    
    -0.92
    ။
    -0.92
    çamento
    -0.90
    ɵɵ
    -0.90
    ])),
    -0.88
    folgung
    -0.88
    POSITIVE LOGITS
     it
    1.27
     these
    1.27
     this
    1.13
    alogie
    1.02
     recently
    0.98
    它
    0.97
     equivalente
    0.94
    шень
    0.92
    וּ
    0.91
    另一
    0.91
    Activations Density 0.046%

    No Known Activations