© 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. 54185
    Prev
    Next
    INDEX
    Explanations

    specific names and types

    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
     sendok
    -1.17
     fuir
    -1.06
     复古
    -1.04
    Nazwa
    -1.04
     armi
    -1.03
     بانک
    -1.02
     kimia
    -1.02
     barca
    -1.00
     coreano
    -1.00
    tku
    -0.99
    POSITIVE LOGITS
     וה
    1.05
    C
    0.96
    R
    0.93
     They
    0.92
    w
    0.88
    <tbody>
    0.86
     a
    0.86
    T
    0.85
     de
    0.84
     The
    0.84
    Activations Density 0.371%

    No Known Activations