© 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. 38910
    Prev
    Next
    INDEX
    Explanations

    classed as or reputed

    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
    菝
    -3.28
    媗
    -3.08
    辚
    -3.00
     onze
    -2.73
    that
    -2.72
    蠃
    -2.69
    迓
    -2.67
     expérience
    -2.63
     tyle
    -2.63
     که
    -2.58
    POSITIVE LOGITS
    寕
    2.83
    风的
    2.34
     Their
    2.34
     weißem
    2.34
    ...!
    2.33
     Vordergrund
    2.33
    鬟
    2.28
    って思
    2.27
     grüne
    2.27
     Obtaining
    2.25
    Activations Density 0.019%

    No Known Activations