© 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. 10-GEMMASCOPE-RES-131K
    7. 86208
    Prev
    Next
    INDEX
    Explanations

    locations relative to things

    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_10/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
    надца
    -1.60
    喈
    -1.50
    0
    -1.47
     ТАК
    -1.39
    وقد
    -1.38
    mA
    -1.32
     podoba
    -1.32
     dieną
    -1.30
     Irán
    -1.30
    年底
    -1.30
    POSITIVE LOGITS
     but
    1.64
     [...]
    1.59
    StoryboardSegue
    1.41
     amused
    1.40
     you
    1.38
    gencias
    1.37
     différence
    1.32
    举办
    1.32
    most
    1.31
     деву
    1.31
    Activations Density 0.025%

    No Known Activations