© 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. 100875
    Prev
    Next
    INDEX
    Explanations

    by [X]

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

    if/then structures

    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
     enablement
    0.51
    ്രീ
    0.46
    یند
    0.43
    таны
    0.42
    𒈾
    0.42
     montrent
    0.42
    ক্ষিতে
    0.41
     ہیں۔
    0.40
     imagery
    0.40
    ഴിലാ
    0.40
    POSITIVE LOGITS
     Cyril
    0.44
     Storm
    0.44
     ck
    0.43
     P
    0.43
     Bxc
    0.43
     takich
    0.43
     Nicholas
    0.42
     Flash
    0.42
     самим
    0.42
     B
    0.41
    Activations Density 0.001%

    No Known Activations