© 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. 216685
    Prev
    Next
    INDEX
    Explanations

    specific phrases after certain words

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

    cats goddesses mummification

    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
     amenities
    0.52
    न
    0.52
     oint
    0.51
    онів
    0.51
    ن
    0.50
    数
    0.49
    லூர்
    0.48
    ক
    0.46
     exist
    0.46
    র্য
    0.46
    POSITIVE LOGITS
     handset
    0.46
     Nort
    0.45
    创始人
    0.45
    Normalized
    0.45
     Verizon
    0.45
    螌
    0.44
    负责人
    0.44
    呠
    0.44
    credit
    0.43
     Counselor
    0.42
    Activations Density 0.000%

    No Known Activations