© 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. 57124
    Prev
    Next
    INDEX
    Explanations

    numbers and degrees

    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
     raken
    -0.74
    Tis
    -0.73
     棚
    -0.72
    BD
    -0.70
     trein
    -0.68
     Skyline
    -0.68
    下拉
    -0.68
    INE
    -0.68
    hed
    -0.67
    лет
    -0.67
    POSITIVE LOGITS
     RR
    1.25
     YY
    1.19
     DD
    1.16
     JJ
    1.12
     HH
    1.12
     GG
    1.04
     PP
    1.03
     ОО
    1.02
     UU
    1.01
    ddin
    1.01
    Activations Density 0.038%

    No Known Activations