© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 140026
    Prev
    Next
    INDEX
    Explanations

    I will

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

    explaining concepts and defining terms

    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
    Negative Logits
     lingk
    0.48
    WindowClass
    0.42
     fal
    0.42
     generally
    0.41
    generally
    0.40
     смотри
    0.40
     generalmente
    0.40
    িন্দ
    0.39
    imbra
    0.39
    启
    0.38
    POSITIVE LOGITS
    ક
    0.48
     मस्
    0.47
    之間
    0.47
     ήταν
    0.46
     পাওয়া
    0.46
     વચ્ચે
    0.46
    ᔕ
    0.46
     बीच
    0.46
     भाषा
    0.46
     μέρος
    0.46
    Activations Density 0.009%

    No Known Activations