© 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. 165074
    Prev
    Next
    INDEX
    Explanations

    collocations and common phrases

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

    Banking Trojans

    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
    ມີ
    0.49
     comprim
    0.46
     Grandpa
    0.44
     constricted
    0.44
     confined
    0.44
     Tuesdays
    0.43
    ချုပ်
    0.43
    ม
    0.42
    نم
    0.42
    ルー
    0.42
    POSITIVE LOGITS
     для
    0.49
    čke
    0.46
    для
    0.44
    izioni
    0.43
    Exponential
    0.43
    ᴾ
    0.43
    Для
    0.42
    ček
    0.42
    สำหรับ
    0.42
     สําหรับ
    0.41
    Activations Density 0.000%

    No Known Activations