© 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. 133218
    Prev
    Next
    INDEX
    Explanations

    automatically blocks

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

    declining harmful or illegal requests

    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
     millones
    0.49
    Millions
    0.49
    американ
    0.46
    の
    0.45
     みんな
    0.44
    ની
    0.44
     dönem
    0.44
     milyon
    0.44
     Millionen
    0.44
     ameryka
    0.44
    POSITIVE LOGITS
     argument
    0.50
    ลาย
    0.50
    键
    0.46
    ר
    0.45
    处理器
    0.44
    花费
    0.44
    箫
    0.44
     containing
    0.43
    指
    0.42
    服务器
    0.42
    Activations Density 0.000%

    No Known Activations