© 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. 29547
    Prev
    Next
    INDEX
    Explanations

    financial reporting or couple's finances

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

    plots against monarchs

    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
    ्वती
    0.51
     équipé
    0.46
    ंपरिक
    0.46
     newcom
    0.46
    pperm
    0.46
     ២
    0.46
     صنایع
    0.45
    ંતુ
    0.45
     ರೀತಿಯ
    0.44
     বাঙালী
    0.44
    POSITIVE LOGITS
    管理的
    0.44
    C
    0.43
     нео
    0.43
     hled
    0.42
    糙
    0.41
     床
    0.41
    R
    0.40
    入
    0.40
     jail
    0.40
     lact
    0.40
    Activations Density 0.000%

    No Known Activations