© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3754
    Prev
    Next
    INDEX
    Explanations

    cancel

    np_acts-logits-general · gemini-2.5-flash-lite

    algebraic equation solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erections
    0.41
     renting
    0.40
     convexity
    0.39
    嬋
    0.39
    ्युनिकेशन
    0.38
     rentals
    0.38
     eyeglasses
    0.38
    魃
    0.38
     канализа
    0.37
     Shab
    0.37
    POSITIVE LOGITS
    cancel
    1.31
     cancel
    1.27
     cancels
    1.19
     cancelled
    1.18
     cancellation
    1.17
     canceled
    1.14
     cancelación
    1.14
     Cancel
    1.13
    Cancel
    1.13
    cancelled
    1.09
    Activations Density 0.013%

    No Known Activations