© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33820
    Prev
    Next
    INDEX
    Explanations

    array, file, do

    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
    SÍ
    -0.93
    рони
    -0.88
    executable
    -0.87
     titulaire
    -0.85
     alemana
    -0.84
     pueden
    -0.84
     puede
    -0.82
     Combining
    -0.82
    nament
    -0.81
     beberapa
    -0.81
    POSITIVE LOGITS
    cc
    1.19
    l
    1.07
    lls
    0.97
    c
    0.97
    ll
    0.94
    L
    0.94
    Ris
    0.83
     ''}
    0.81
     bohat
    0.81
     Plenty
    0.79
    Activations Density 0.001%

    No Known Activations