© 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. 22-GEMMASCOPE-RES-131K
    7. 39798
    Prev
    Next
    INDEX
    Explanations

    code structure and completion

    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
    LLLL
    -1.14
    didSet
    -1.14
    だけでなく
    -1.14
    umers
    -1.14
     continually
    -1.10
     IconData
    -1.08
     NOT
    -1.08
    也在
    -1.07
     soprattutto
    -1.06
     significantly
    -1.05
    POSITIVE LOGITS
    Before
    1.73
    During
    1.70
    Shortly
    1.66
    After
    1.59
    Despite
    1.55
    Since
    1.51
    Through
    1.47
    You
    1.43
    Every
    1.39
    Mô
    1.39
    Activations Density 0.001%

    No Known Activations