© 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. 199420
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    validate purchase or transaction

    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
    meshes
    0.52
     হিন্দুর
    0.45
    laublich
    0.45
    ljena
    0.44
     splitpos
    0.43
     하나님의
    0.43
     unaff
    0.43
    淉
    0.43
    goatee
    0.42
    basecode
    0.42
    POSITIVE LOGITS
     October
    0.47
    Thomas
    0.44
     noviembre
    0.44
     octubre
    0.44
    ประมาณ
    0.44
    平成
    0.44
     octobre
    0.44
     aproximadamente
    0.43
    Breast
    0.43
     Libro
    0.43
    Activations Density 0.001%

    No Known Activations