© 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. 233086
    Prev
    Next
    INDEX
    Explanations

    Gendered application fees

    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
     –
    0.48
     丶
    0.47
    ac
    0.45
     Alaska
    0.45
     –,
    0.44
    cdn
    0.43
     ओलंपिक
    0.42
     通常
    0.42
     整
    0.42
    DataContext
    0.41
    POSITIVE LOGITS
     maintien
    0.54
     utilisent
    0.52
    hankelijk
    0.52
     unul
    0.50
    ivät
    0.47
     ponownie
    0.47
     पुढील
    0.46
     mirip
    0.45
     اینکه
    0.45
    เหมือน
    0.45
    Activations Density 0.003%

    No Known Activations