© 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. 172204
    Prev
    Next
    INDEX
    Explanations

    common word pairs

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

    loses its strength

    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
    이다
    0.46
    者
    0.45
    祿
    0.44
    幹
    0.44
    DSL
    0.43
    加
    0.43
    布
    0.43
    専門店
    0.42
    泉
    0.42
    矣
    0.42
    POSITIVE LOGITS
     відпо
    0.49
    nelly
    0.48
     ليك
    0.48
     झरने
    0.47
     найбіль
    0.47
    quellen
    0.46
     كلمات
    0.46
     kijk
    0.46
    hap
    0.45
    чну
    0.45
    Activations Density 0.000%

    No Known Activations