© 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. 135047
    Prev
    Next
    INDEX
    Explanations

    phrases after 'the' and 'surgical'

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

    technical terms and suffixes

    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
    咏
    0.47
     paisaje
    0.45
     Awakening
    0.44
     bruger
    0.44
     Friends
    0.44
     Entertainment
    0.43
     kirj
    0.43
    রাও
    0.43
     TabLayout
    0.43
     Acting
    0.42
    POSITIVE LOGITS
    ಋ
    0.48
    örung
    0.46
    oula
    0.46
    бота
    0.43
    ごとに
    0.43
    ASP
    0.42
     し
    0.42
    였다
    0.42
    äure
    0.41
    ❑
    0.41
    Activations Density 0.000%

    No Known Activations