© 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. 22-GEMMASCOPE-RES-131K
    7. 35043
    Prev
    Next
    INDEX
    Explanations

    definitions, discussion, treatment, meaning

    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_22/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
     this
    -1.66
     since
    -1.27
    erweise
    -1.20
     because
    -1.15
    yní
    -1.14
     even
    -1.10
     wouldn
    -1.10
     every
    -1.10
    occu
    -1.05
     persino
    -1.05
    POSITIVE LOGITS
     vocale
    1.15
    🤮
    1.15
    🤢
    1.13
     we
    1.13
    我们
    1.13
     briefly
    1.08
     Palestina
    1.04
    devším
    1.03
     medan
    1.03
     необходи
    1.03
    Activations Density 0.013%

    No Known Activations