© 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. 8754
    Prev
    Next
    INDEX
    Explanations

    YouTube and videos

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

    YouTube videos

    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
    𝐿
    0.43
    文學
    0.43
    EARCH
    0.42
     النصوص
    0.41
     }^{\
    0.40
    兩
    0.40
    парта
    0.39
     литератур
    0.39
    函數
    0.39
    螻
    0.39
    POSITIVE LOGITS
     YouTube
    0.73
    youtube
    0.73
     Youtube
    0.72
     youtube
    0.65
    Youtube
    0.64
    YouTube
    0.63
     YouT
    0.61
     유튜브
    0.59
     відео
    0.56
     यूट्यूब
    0.54
    Activations Density 0.000%

    No Known Activations