© 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. 220633
    Prev
    Next
    INDEX
    Explanations

    households and businesses

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

    defining scope and purpose

    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
     asymmetries
    0.49
    sparsity
    0.49
    ylmethylsulfanyl
    0.49
     discontinuities
    0.48
    UnaryOperation
    0.47
     anomalies
    0.47
    ;"+
    0.46
    پ
    0.46
    阂
    0.46
    
    0.46
    POSITIVE LOGITS
     on
    0.55
     nab
    0.53
    ches
    0.47
    árd
    0.45
    ánd
    0.44
    jam
    0.44
     laying
    0.44
    стром
    0.43
    紛
    0.43
     reag
    0.43
    Activations Density 0.000%

    No Known Activations