© 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. 142954
    Prev
    Next
    INDEX
    Explanations

    being known

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

    technical summaries and solutions

    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
     組
    0.49
     רי
    0.48
     Chrysler
    0.46
    ęła
    0.45
     materiale
    0.45
     Atatürk
    0.44
     Invent
    0.44
     ইঞ্জিন
    0.44
     Compressed
    0.44
     조선
    0.43
    POSITIVE LOGITS
    윽
    0.53
     celebs
    0.49
    ilation
    0.47
    stadt
    0.46
    াবদ্ধ
    0.46
    쿠
    0.43
    들이
    0.43
     celeb
    0.42
     untenable
    0.42
    剱
    0.42
    Activations Density 0.000%

    No Known Activations