© 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. 217461
    Prev
    Next
    INDEX
    Explanations

    paper. hours. biomarkers, territory, Filipino after

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

    how, immediately, feel, recommend, reach

    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
    ➥
    0.53
    🚦
    0.53
     канализа
    0.53
    🚄
    0.52
     माध्य
    0.50
    🛤
    0.50
     यात्री
    0.49
    ➤
    0.49
    बाग
    0.49
     канали
    0.48
    POSITIVE LOGITS
     SCS
    0.48
     eigene
    0.45
     Eigent
    0.44
     MF
    0.43
     entretien
    0.43
     voluto
    0.42
     One
    0.41
     The
    0.41
     elf
    0.41
    1
    0.41
    Activations Density 0.001%

    No Known Activations