© 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. 101380
    Prev
    Next
    INDEX
    Explanations

    foil materials

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

    competition or enumeration sequence

    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
    一台
    0.46
    ermodel
    0.43
    覀
    0.43
    Global
    0.43
    ьогодні
    0.43
    今天的
    0.42
    旲
    0.41
     душа
    0.41
    Wind
    0.41
    佲
    0.41
    POSITIVE LOGITS
     worsens
    0.62
     deficits
    0.59
     stadiums
    0.55
     scarves
    0.55
     albi
    0.55
     inhomogeneities
    0.54
     escapes
    0.54
     theorists
    0.53
     blobs
    0.53
     maturities
    0.53
    Activations Density 0.001%

    No Known Activations