© 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. 40095
    Prev
    Next
    INDEX
    Explanations

    using something with authority

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

    knowledge base, AWS, fires, valuable, skepticism

    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
    唝
    0.48
    Establish
    0.46
     शोषण
    0.43
     antagon
    0.43
    skar
    0.43
    rawberry
    0.42
    Boot
    0.42
     শতাব্দীর
    0.42
    Latency
    0.42
    numberOf
    0.41
    POSITIVE LOGITS
    '
    0.51
     мав
    0.49
    ות
    0.47
     од
    0.47
    льної
    0.45
     τραγ
    0.45
    বল
    0.45
     rehabilitated
    0.45
     добы
    0.44
     Ах
    0.43
    Activations Density 0.000%

    No Known Activations