© 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. 23359
    Prev
    Next
    INDEX
    Explanations

    commercial waste disposal

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

    solving equations

    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
    S
    0.67
    G
    0.55
    미
    0.53
    Super
    0.52
    Ро
    0.52
    Կ
    0.49
    R
    0.49
    Double
    0.48
    IM
    0.48
    E
    0.48
    POSITIVE LOGITS
     contingencies
    0.52
     nucl
    0.51
     minimization
    0.50
     radiolysis
    0.50
     artific
    0.49
     radionu
    0.49
     moc
    0.48
     fermion
    0.47
     radionuclides
    0.47
     detr
    0.47
    Activations Density 0.003%

    No Known Activations