© 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. 175169
    Prev
    Next
    INDEX
    Explanations

    rights, mission, trend, muse, everyone

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

    **freelance vs employed**

    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
    人形
    0.54
    อังกฤษ
    0.51
    اور
    0.50
    human
    0.49
     produkter
    0.49
    ละ
    0.49
    อา
    0.49
    โ
    0.48
    ッ
    0.48
    উপর
    0.47
    POSITIVE LOGITS
     choked
    0.54
    ameen
    0.52
     చె
    0.49
     সহায়
    0.48
     paycheck
    0.47
     competing
    0.46
     unwelcome
    0.46
     wretched
    0.45
     teeming
    0.45
    indentLevel
    0.44
    Activations Density 0.000%

    No Known Activations