© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115567
    Prev
    Next
    INDEX
    Explanations

    contextual suffixes

    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
    e
    -1.76
    d
    -1.74
    a
    -1.68
    B
    -1.64
    al
    -1.56
    P
    -1.54
    v
    -1.54
    N
    -1.53
    w
    -1.52
    o
    -1.52
    POSITIVE LOGITS
     farba
    1.70
     bluz
    1.66
     tunik
    1.65
     granat
    1.63
    کفش
    1.61
     kabát
    1.56
     autocollant
    1.56
     dekol
    1.53
     kré
    1.49
     klat
    1.45
    Activations Density 0.063%

    No Known Activations