© 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. 22-GEMMASCOPE-RES-131K
    7. 27175
    Prev
    Next
    INDEX
    Explanations

    .com profile or obituary

    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_22/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
    umuz
    -0.98
    為に
    -0.97
    줬
    -0.93
    第一步
    -0.90
     uwagę
    -0.90
    Dès
    -0.90
     PHIL
    -0.89
    Matériel
    -0.89
    Coucou
    -0.86
    inizi
    -0.85
    POSITIVE LOGITS
     "
    1.25
     где
    1.13
    による
    1.12
    ̎
    1.10
     ""
    1.02
    关于
    1.00
    etal
    0.98
    での
    0.98
     "'
    0.98
     под
    0.98
    Activations Density 0.085%

    No Known Activations