© 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. 60828
    Prev
    Next
    INDEX
    Explanations

    citations and author initials

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

    love, language, and concepts

    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
     Finanz
    0.53
     Γερμαν
    0.51
    Beverungen
    0.51
    Forces
    0.49
     gemeente
    0.49
     Рим
    0.47
     Deutschland
    0.46
    濟
    0.46
     Ż
    0.46
    បញ្ចូល
    0.46
    POSITIVE LOGITS
    وینت
    0.50
    𝒄
    0.46
    лит
    0.46
    omorphisms
    0.46
     طبیعی
    0.45
     noved
    0.45
    فیر
    0.45
    nSamples
    0.43
    स्ड
    0.42
    چنین
    0.42
    Activations Density 0.002%

    No Known Activations