© 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. 149169
    Prev
    Next
    INDEX
    Explanations

    data management and content

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

    sexual act or error handling

    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
     způ
    0.46
    ObjectUnderTest
    0.44
    㮍
    0.44
     وغير
    0.43
     Archaeology
    0.42
     المراجعه
    0.40
    软件包
    0.40
    还好
    0.40
    নমেন্ট
    0.40
    Responder
    0.39
    POSITIVE LOGITS
    ùi
    0.49
    ồi
    0.49
    오
    0.48
    オ
    0.46
     ૧
    0.45
    صل
    0.44
     तथ
    0.44
    ț
    0.44
    𝗲
    0.44
     HENRY
    0.44
    Activations Density 0.001%

    No Known Activations