© 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. 7636
    Prev
    Next
    INDEX
    Explanations

    phrases like "has expired", "would like"

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

    list items or section titles

    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
    an
    0.51
     Landkreis
    0.50
     su
    0.49
     ក
    0.48
     ALS
    0.48
     സെക്രട്ട
    0.46
    oe
    0.46
     thugs
    0.46
    oters
    0.46
     บอก
    0.45
    POSITIVE LOGITS
     económ
    0.49
    ным
    0.48
    ㅝ
    0.47
    笛
    0.47
     académ
    0.45
     presup
    0.44
     geográfica
    0.44
     múltipl
    0.44
     geographical
    0.43
     nasional
    0.43
    Activations Density 0.000%

    No Known Activations