© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10626
    Prev
    Next
    INDEX
    Explanations

    why are

    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
     have
    -1.75
     eager
    -1.71
    },
    -1.66
    푣
    -1.62
    晅
    -1.59
    ဴ
    -1.55
     epitom
    -1.52
     tries
    -1.51
    เหร
    -1.50
    
    -1.50
    POSITIVE LOGITS
    .
    1.81
    recommend
    1.81
    "
    1.73
    helps
    1.65
    excellent
    1.64
    
    1.63
    creating
    1.62
    makes
    1.62
     réaliser
    1.61
    takes
    1.59
    Activations Density 0.002%

    No Known Activations