© 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. 14483
    Prev
    Next
    INDEX
    Explanations

    location names before of

    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
     verschiedene
    -1.59
     different
    -1.48
     broader
    -1.40
     べ
    -1.39
     vielleicht
    -1.39
    different
    -1.39
    other
    -1.29
     다른
    -1.28
     diferentes
    -1.26
     diversa
    -1.26
    POSITIVE LOGITS
     of
    5.66
     öğretmen
    1.41
     čier
    1.41
     откри
    1.37
     pomocou
    1.30
     bilde
    1.30
    НАЯ
    1.30
    fél
    1.26
     óra
    1.24
     būt
    1.23
    Activations Density 0.035%

    No Known Activations