© 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. 51818
    Prev
    Next
    INDEX
    Explanations

    part and parcel, shelter

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

    spiritual/philosophical 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
    ravel
    0.47
    黔
    0.41
    Symfony
    0.40
    PHP
    0.40
     processes
    0.39
     Mindanao
    0.39
     setSelected
    0.39
    Parameteri
    0.38
     Symfony
    0.38
     GetData
    0.37
    POSITIVE LOGITS
     favorit
    0.50
     Jorg
    0.48
     recomendado
    0.47
    嘬
    0.46
     حسين
    0.44
    জেল
    0.43
    ቱን
    0.42
     ऑर
    0.42
     குறிப்பாக
    0.42
     ব্র্যান্ড
    0.41
    Activations Density 0.010%

    No Known Activations