© 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. 234182
    Prev
    Next
    INDEX
    Explanations

    financial reviews and issues

    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
    ച
    0.52
    ビ
    0.49
    範圍
    0.49
    ційний
    0.49
    椀
    0.48
    ্গ
    0.48
    δ
    0.47
    nc
    0.46
    ϙ
    0.46
    สัง
    0.46
    POSITIVE LOGITS
     expats
    0.55
     day
    0.54
     looting
    0.51
     piya
    0.48
     sehari
    0.47
     donors
    0.47
     burung
    0.47
     unpaid
    0.46
     migrant
    0.46
     blackmail
    0.46
    Activations Density 0.001%

    No Known Activations