© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2530
    Prev
    Next
    INDEX
    Explanations

    TV and radio media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ių
    0.38
     মোর
    0.38
     Essence
    0.37
     Burger
    0.36
    ("--------
    0.35
    孙
    0.34
    饿
    0.34
     构建
    0.34
     mora
    0.33
    充满
    0.33
    POSITIVE LOGITS
    番組
    0.56
    📺
    0.54
    节目
    0.53
     stations
    0.52
     station
    0.49
     tv
    0.49
    电视
    0.49
     TV
    0.49
    tv
    0.48
     televisión
    0.47
    Activations Density 0.007%

    No Known Activations