© 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. 34-GEMMASCOPE-RES-131K
    7. 1648
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
     даже
    -1.37
     even
    -1.30
     nawet
    -1.25
    0
    -1.17
     навіть
    -1.13
     incluso
    -1.06
     jopa
    -1.02
     they
    -1.00
    even
    -0.96
    رر
    -0.96
    POSITIVE LOGITS
    herself
    1.22
    ėjimas
    1.21
     again
    1.17
    那些
    1.13
    tillinger
    1.11
     those
    1.08
    those
    1.06
    ૪
    1.03
    himself
    1.03
     město
    1.02
    Activations Density 0.073%

    No Known Activations