© 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. 34-GEMMASCOPE-RES-131K
    7. 2639
    Prev
    Next
    INDEX
    Explanations

    open followed by different contexts

    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_34/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
    Opening
    -0.91
    zah
    -0.82
     OPENING
    -0.80
    ੋ
    -0.79
     byen
    -0.78
    OPENING
    -0.76
    bps
    -0.74
    タオル
    -0.72
     marvelous
    -0.72
     wonderful
    -0.71
    POSITIVE LOGITS
     ended
    1.60
     open
    1.46
     ends
    1.10
     spaces
    1.07
     Ended
    1.05
    open
    1.04
     allowing
    1.01
     space
    1.00
    Open
    0.99
     Open
    0.99
    Activations Density 0.028%

    No Known Activations