© 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. 62869
    Prev
    Next
    INDEX
    Explanations

    an apparent / almost all

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

    hydroxylation steps

    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
    ОР
    0.55
    Specifically
    0.53
    특히
    0.52
    모
    0.52
    Ნ
    0.52
    Ар
    0.50
    Sov
    0.50
    Nä
    0.49
    Пере
    0.49
    პ
    0.49
    POSITIVE LOGITS
     millimeters
    0.52
     ge
    0.51
     stored
    0.49
     macer
    0.48
     got
    0.48
     chond
    0.48
     odometer
    0.48
     filament
    0.47
     dues
    0.47
     atmospheric
    0.46
    Activations Density 0.000%

    No Known Activations