© 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. 105476
    Prev
    Next
    INDEX
    Explanations

    money is

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

    game or system structure

    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
    nić
    0.51
    ρώ
    0.44
    ляция
    0.44
    zq
    0.43
    ামী
    0.42
    るので
    0.42
    ーツ
    0.42
    ि
    0.42
    在
    0.42
    ڱ
    0.41
    POSITIVE LOGITS
     isomers
    0.56
     Gun
    0.50
     Firearms
    0.50
     Medic
    0.49
     Modeling
    0.48
     modeling
    0.48
     Chemicals
    0.48
     Republicans
    0.48
     Fighting
    0.48
    fighting
    0.48
    Activations Density 0.000%

    No Known Activations