© 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. 73214
    Prev
    Next
    INDEX
    Explanations

    phrases that use specific word pairings

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

    checking related to

    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
     जाधव
    0.42
     የሆነ
    0.41
    oly
    0.41
     مغ
    0.40
     ଗ
    0.40
     피부
    0.39
    ंड
    0.39
     حد
    0.39
    wallet
    0.39
     низ
    0.38
    POSITIVE LOGITS
     furthermore
    0.47
     Sapir
    0.47
    ４
    0.45
    假设
    0.45
    并且
    0.44
     Oaxaca
    0.44
     Ubuy
    0.44
     Kassel
    0.44
     Chernobyl
    0.43
    书
    0.42
    Activations Density 0.000%

    No Known Activations