© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 42737
    Prev
    Next
    INDEX
    Explanations

    postcard prints

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

    minimize and Mermaid

    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
    ítulos
    0.53
    _*
    0.50
    mDatas
    0.49
    érences
    0.49
    undred
    0.48
    SCs
    0.48
    ubes
    0.47
     обществе
    0.47
    ölker
    0.46
    ígenes
    0.46
    POSITIVE LOGITS
     koko
    0.51
    จ
    0.50
     duplo
    0.50
     taip
    0.48
     keluar
    0.48
     raport
    0.47
    تا
    0.47
     quotid
    0.46
    ותו
    0.46
    ใน
    0.46
    Activations Density 0.000%

    No Known Activations