© 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. 115188
    Prev
    Next
    INDEX
    Explanations

    pass band, capitalisation rate, component part

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

    if/then conditional logic

    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
     H
    0.61
     Be
    0.57
     mit
    0.57
     B
    0.56
     Le
    0.55
     the
    0.55
     St
    0.55
     Cleveland
    0.55
     T
    0.54
     Chipotle
    0.54
    POSITIVE LOGITS
    יל
    0.70
    ал
    0.69
    ཥ
    0.68
     TRANSPORTURI
    0.67
    ཋ
    0.67
    אי
    0.66
    ור
    0.65
    ל
    0.65
    שי
    0.64
    ЛИ
    0.64
    Activations Density 0.035%

    No Known Activations