© 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. 148391
    Prev
    Next
    INDEX
    Explanations

    most popular

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

    election, growing disconnect, gap in, patrol, plates

    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
    যু
    0.43
     qualifies
    0.43
     pilot
    0.42
    ביע
    0.42
    顶
    0.42
    بيق
    0.41
     sustains
    0.41
     grazed
    0.41
     piloted
    0.40
     thickly
    0.40
    POSITIVE LOGITS
     активи
    0.52
     भिन्न
    0.51
     teri
    0.51
    essä
    0.50
     पॉलि
    0.49
    cau
    0.49
    هم
    0.49
     Ў
    0.48
    猢
    0.48
    assing
    0.47
    Activations Density 0.000%

    No Known Activations