© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1108
    Prev
    Next
    INDEX
    Explanations

    . import, . xq, . xq, .EXE, .The

    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
     Confirm
    -0.92
    Blas
    -0.81
     Confirmation
    -0.72
     confirming
    -0.72
    Confirm
    -0.71
     confirms
    -0.71
     brazilian
    -0.70
     estando
    -0.68
    enterian
    -0.68
    uais
    -0.68
    POSITIVE LOGITS
    RequestOptions
    0.82
     kari
    0.81
     convex
    0.81
     апте
    0.78
     zor
    0.77
    zor
    0.76
     Oaks
    0.76
     kol
    0.76
    optic
    0.74
     senin
    0.74
    Activations Density 0.049%

    No Known Activations