© 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. 35343
    Prev
    Next
    INDEX
    Explanations

    cables, fibers, and tubing

    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
     
    -1.40
     čás
    -0.99
     ähn
    -0.99
     листь
    -0.98
    ámicas
    -0.98
    наго
    -0.97
    ilber
    -0.97
     ')'
    -0.97
    ynchronously
    -0.97
    enging
    -0.97
    POSITIVE LOGITS
     between
    1.14
    િ
    1.12
    iliares
    1.11
    လ
    1.09
     HomeComponent
    1.09
    sikker
    1.09
    endimiento
    1.09
    牀
    1.08
     官网
    1.08
     tässä
    1.08
    Activations Density 0.113%

    No Known Activations