© 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. 131162
    Prev
    Next
    INDEX
    Explanations

    legal and administrative documents

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

    breakdown and features

    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
    rennt
    0.50
    nahmen
    0.49
     ′
    0.49
    rierte
    0.48
     ות
    0.48
     Zahlung
    0.47
    颀
    0.47
    kennt
    0.47
    ្រី
    0.47
    ഽ
    0.47
    POSITIVE LOGITS
    သင့်
    0.46
    Background
    0.45
    обы
    0.45
    وري
    0.43
     panneau
    0.43
    על
    0.42
     unwelcome
    0.42
    Business
    0.41
    顏色
    0.41
     unnecessary
    0.41
    Activations Density 0.001%

    No Known Activations