© 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. 125491
    Prev
    Next
    INDEX
    Explanations

    countries and languages

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

    inflation, costs, supply, sand, conditions

    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
     internal
    0.47
     internally
    0.45
     iterable
    0.44
     giao
    0.44
    )^{-\
    0.42
     ray
    0.41
     cú
    0.41
     داخلی
    0.41
     infotainment
    0.41
     pengunjung
    0.40
    POSITIVE LOGITS
    जैसा
    0.56
    ﻴ
    0.53
    și
    0.52
    ㅝ
    0.51
    쫓
    0.49
    april
    0.48
    赞
    0.48
    아서
    0.48
    صار
    0.47
    advised
    0.47
    Activations Density 0.001%

    No Known Activations