© 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. 99045
    Prev
    Next
    INDEX
    Explanations

    types of people or groups

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

    groups and income levels

    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
    Reverse
    0.50
    a
    0.49
    as
    0.47
    なの
    0.46
    i
    0.46
    il
    0.46
    ata
    0.46
     Reverse
    0.46
    ঃ
    0.46
    \
    0.45
    POSITIVE LOGITS
     businessmen
    0.55
     enthusiasts
    0.54
     bureaucrats
    0.53
     admirers
    0.52
     accueil
    0.52
     microphones
    0.50
     innovators
    0.49
     prolet
    0.49
     conservatives
    0.48
    <unused32>
    0.48
    Activations Density 0.001%

    No Known Activations