© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45286
    Prev
    Next
    INDEX
    Explanations

    linear equations and algebra

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

    linear equations and functions

    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_31_width_262k_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
    Е
    0.54
    нда
    0.52
     était
    0.48
    埃
    0.48
    HOLD
    0.47
     chewed
    0.45
     É
    0.45
    िनल
    0.44
     erroneously
    0.44
    ч
    0.44
    POSITIVE LOGITS
     hasattr
    0.46
     globalMap
    0.45
     startActivity
    0.45
    unehm
    0.44
     आरआर
    0.44
     সংসারে
    0.44
     dobb
    0.44
     morphism
    0.43
     आंच
    0.42
    system
    0.42
    Activations Density 0.001%

    No Known Activations