© 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. 39876
    Prev
    Next
    INDEX
    Explanations

    CTR 3, __LP, Ursus

    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
    al
    -2.52
    d
    -2.36
     If
    -2.19
     interplay
    -2.06
    
    -2.05
    Two
    -2.05
    ⚋
    -2.05
    3
    -2.03
    First
    -1.99
    and
    -1.97
    POSITIVE LOGITS
    ྅
    2.66
     Vordergrund
    2.41
     voegen
    2.16
     Hinblick
    2.13
     achten
    2.08
    
    2.06
     constitución
    2.02
    錼
    2.00
     besondere
    1.99
     mauva
    1.98
    Activations Density 0.000%

    No Known Activations