© 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. 238245
    Prev
    Next
    INDEX
    Explanations

    love, love, love

    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
    𝖔
    0.48
     сотрудник
    0.46
    монт
    0.46
     Boats
    0.45
     персонал
    0.45
     উদ্ভিদ
    0.44
     сдела
    0.44
     получаем
    0.44
    鎸
    0.44
    唓
    0.43
    POSITIVE LOGITS
     masas
    0.47
    ravi
    0.46
    gmail
    0.46
    み
    0.44
    phor
    0.44
    دید
    0.44
    riz
    0.43
    mese
    0.43
    redos
    0.43
    it
    0.42
    Activations Density 0.001%

    No Known Activations