© 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. 10-GEMMASCOPE-RES-131K
    7. 113245
    Prev
    Next
    INDEX
    Explanations

    places named garden

    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
    簟
    -3.09
    ܜ
    -2.67
     magasiner
    -2.59
    樒
    -2.50
    釤
    -2.44
    ⎚
    -2.41
    
    -2.38
     petto
    -2.34
    ейчас
    -2.31
    сторінку
    -2.30
    POSITIVE LOGITS
    ↵↵
    2.86
    -
    2.41
    :
    2.34
    m
    2.30
    ，
    2.22
    ’
    2.19
     unwavering
    2.16
    </h3>
    2.13
     nueva
    2.08
     haciendo
    2.06
    Activations Density 0.005%

    No Known Activations