© 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. 99148
    Prev
    Next
    INDEX
    Explanations

    announcements and debuts

    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
    exits
    -0.82
    BottomSheet
    -0.72
    OFFER
    -0.71
    chap
    -0.71
    isser
    -0.70
    otropy
    -0.69
    ("*");
    -0.68
     היו
    -0.68
     Chap
    -0.68
    Mog
    -0.66
    POSITIVE LOGITS
     spy
    2.05
     spied
    1.75
     spies
    1.51
     camouflage
    1.48
    spy
    1.42
     Spy
    1.42
     prototypes
    1.31
     teaser
    1.30
    Spy
    1.27
     prototype
    1.21
    Activations Density 0.032%

    No Known Activations