© 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. 161874
    Prev
    Next
    INDEX
    Explanations

    words following 'the'

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

    going global

    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
     স্নে
    0.46
    ponenten
    0.45
     അദ്ദേഹ
    0.44
    สนับสนุน
    0.43
    ༧
    0.42
     선생님
    0.42
    導演
    0.42
    ધી
    0.42
    ീയ
    0.42
    บริหาร
    0.41
    POSITIVE LOGITS
     kilow
    0.51
    ful
    0.50
    ｎ
    0.47
    Gin
    0.46
     Gin
    0.44
     मोठा
    0.44
    gers
    0.44
     अश
    0.43
     sez
    0.43
     n
    0.43
    Activations Density 0.000%

    No Known Activations