© 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. 35995
    Prev
    Next
    INDEX
    Explanations

    highest emissions, freely adjusted

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

    Immediate Mode GUI

    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
     decembrie
    0.48
    dengan
    0.44
    porque
    0.43
     begrij
    0.42
    matu
    0.38
    told
    0.38
     opportune
    0.38
     ۽
    0.38
    understand
    0.38
    financed
    0.38
    POSITIVE LOGITS
     خرید
    0.48
     WebDriver
    0.48
     ተጨማሪ
    0.47
     Added
    0.47
     其他
    0.47
     ఇతర
    0.46
     optionally
    0.45
     شیر
    0.44
     kebab
    0.44
     ሌሎች
    0.44
    Activations Density 0.000%

    No Known Activations