© 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. 169872
    Prev
    Next
    INDEX
    Explanations

    clearing rubbish, investment, contract

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

    illegal, unclaimed, advertising

    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
    缔
    0.48
    隐藏
    0.47
    более
    0.46
     बना
    0.46
    色
    0.46
    定める
    0.45
    这就
    0.45
     ถึง
    0.45
    ल
    0.44
    зре
    0.44
    POSITIVE LOGITS
     symplectic
    0.51
     tshirt
    0.50
     watercolour
    0.47
     quantifiable
    0.45
     सिंचाई
    0.44
     beer
    0.43
     trousers
    0.43
     torsional
    0.42
     transpiration
    0.42
     primos
    0.42
    Activations Density 0.001%

    No Known Activations