© 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. 59155
    Prev
    Next
    INDEX
    Explanations

    students learning and reading

    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
     ribuan
    -0.84
    teaching
    -0.81
     mengajar
    -0.81
    issue
    -0.80
     penga
    -0.80
    forged
    -0.79
     pihaknya
    -0.78
     invitado
    -0.77
    atı
    -0.77
     Outils
    -0.76
    POSITIVE LOGITS
     learn
    1.23
     practice
    1.17
     identify
    1.04
     discover
    1.00
     discuss
    0.99
     identificar
    0.97
     hypothe
    0.94
     identifying
    0.94
     learns
    0.93
     read
    0.91
    Activations Density 0.032%

    No Known Activations