© 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. 43799
    Prev
    Next
    INDEX
    Explanations

    reason for

    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
     to
    -1.93
    
    -1.92
     Another
    -1.90
     forceful
    -1.76
     also
    -1.76
     heartbreaking
    -1.73
     picturesque
    -1.70
    :
    -1.69
    )
    -1.65
     tricks
    -1.63
    POSITIVE LOGITS
     navires
    1.93
     bâtiments
    1.82
    romatic
    1.70
     vaisseaux
    1.70
     cœurs
    1.70
     gekocht
    1.69
     lèvres
    1.69
     genoux
    1.68
     matériaux
    1.64
     laajenta
    1.63
    Activations Density 0.037%

    No Known Activations