© 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. 168695
    Prev
    Next
    INDEX
    Explanations

    financial stability, literacy, resources

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

    foreign scripts and names

    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
    that
    0.52
    ライフ
    0.51
    evaluate
    0.50
    慎
    0.49
    po
    0.48
    مان
    0.47
    rite
    0.46
    play
    0.46
    rec
    0.46
    но
    0.45
    POSITIVE LOGITS
     ICS
    0.58
     giriş
    0.55
     ανε
    0.55
     Въ
    0.54
     ข
    0.54
     silam
    0.52
     Aldi
    0.52
     Stiftung
    0.52
     Astr
    0.51
     αντί
    0.51
    Activations Density 0.000%

    No Known Activations