© 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. 5607
    Prev
    Next
    INDEX
    Explanations

    degree, saint, river, top followed by preposition

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

    creation, potential, or power followed by word

    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
    السلام
    0.32
    時間が
    0.31
    所以
    0.30
    সুতরাং
    0.30
     সুতরাং
    0.29
     موجودگی
    0.29
    ungkinkan
    0.28
    㣩
    0.28
     তবুও
    0.28
     gdyż
    0.28
    POSITIVE LOGITS
     of
    0.51
     in
    0.45
     של
    0.44
     của
    0.40
     của
    0.40
     օ
    0.40
     from
    0.39
     în
    0.39
     в
    0.39
     от
    0.38
    Activations Density 0.542%

    No Known Activations