© 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. 2704
    Prev
    Next
    INDEX
    Explanations

    click to action

    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
    衬衫
    -0.88
     Warga
    -0.87
    モニター
    -0.83
    זק
    -0.83
     ļ
    -0.82
    liegende
    -0.82
     auft
    -0.82
    ברי
    -0.81
     chaînes
    -0.81
    都需要
    -0.79
    POSITIVE LOGITS
     see
    1.35
     expand
    1.20
     enlarge
    1.10
     read
    1.07
    Expand
    1.02
    expand
    1.01
    see
    1.01
     visit
    1.00
     reveal
    0.95
     expands
    0.92
    Activations Density 0.009%

    No Known Activations