© 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. 236732
    Prev
    Next
    INDEX
    Explanations

    phrases with "in" and "pro"

    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
     Prescription
    0.52
     ISE
    0.48
     Observing
    0.46
     Office
    0.45
     Serve
    0.45
     lx
    0.45
    γ
    0.45
     Popper
    0.44
     a
    0.43
     Hover
    0.43
    POSITIVE LOGITS
     نتیجه
    0.52
     პრო
    0.51
    代价
    0.47
    哳
    0.47
     نمی
    0.46
     ماه
    0.46
     приро
    0.46
    籹
    0.46
     தொகை
    0.46
    ämä
    0.46
    Activations Density 0.000%

    No Known Activations