© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20719
    Prev
    Next
    INDEX
    Explanations

    duration and consequence

    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
    筈
    -2.08
    ፲
    -1.95
    zelfde
    -1.85
     feront
    -1.81
     zijne
    -1.79
    𝔨
    -1.72
     parut
    -1.72
    zló
    -1.68
     hemel
    -1.67
     hunne
    -1.66
    POSITIVE LOGITS
    -
    2.14
     there
    2.02
     then
    1.91
    )
    1.90
    '
    1.86
     have
    1.84
    ."
    1.70
     but
    1.66
     so
    1.63
    all
    1.61
    Activations Density 0.060%

    No Known Activations