© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22884
    Prev
    Next
    INDEX
    Explanations

    model modelmodel nicknamed, seabed composition

    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
     palabras
    0.41
     словами
    0.40
     знаходи
    0.40
     भाषण
    0.39
    "])
    0.39
     glyph
    0.39
    Columns
    0.38
     மணிய
    0.38
     xAxis
    0.38
    Chunks
    0.38
    POSITIVE LOGITS
    푹
    0.40
     گم
    0.40
    データベース
    0.39
     accompaniment
    0.38
    zee
    0.38
    getMinimum
    0.37
     упаков
    0.37
    što
    0.37
    Torrent
    0.37
    zept
    0.36
    Activations Density 0.000%

    No Known Activations