© 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. 25106
    Prev
    Next
    INDEX
    Explanations

    st followed by specific endings

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

    words starting with st

    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
    6
    1.11
    2
    1.10
    ள்
    1.05
    هاي
    1.00
    5
    0.98
    9
    0.93
    ,
    0.91
    на
    0.88
    ת
    0.88
    spunkt
    0.86
    POSITIVE LOGITS
     اسٹ
    0.99
     ی
    0.97
     آیا
    0.95
     스트
    0.92
     روی
    0.91
     آیات
    0.90
     ای
    0.89
     スト
    0.89
     آی
    0.89
     광
    0.89
    Activations Density 0.245%

    No Known Activations