© 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. 179406
    Prev
    Next
    INDEX
    Explanations

    screws. which

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

    money, personal interactions, and code

    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
     például
    0.44
     U
    0.42
     sch
    0.42
     opens
    0.42
     BO
    0.42
     Ane
    0.41
     B
    0.41
     Opens
    0.40
     H
    0.40
     Mek
    0.40
    POSITIVE LOGITS
    linkColor
    0.46
    娟
    0.46
    यान
    0.45
    १८४
    0.45
    টন
    0.44
    aditional
    0.44
    стта
    0.44
    кистон
    0.44
    стон
    0.44
    ೊಳ್ಳ
    0.43
    Activations Density 0.001%

    No Known Activations