© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    block compounds and specific terms

    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
    وون
    0.54
    쪽에
    0.48
    gle
    0.47
    conflict
    0.45
    cabin
    0.44
    deficit
    0.44
    ෙ
    0.43
    ካ
    0.43
    گیر
    0.42
    гле
    0.41
    POSITIVE LOGITS
     block
    1.08
     Block
    1.05
     Blocks
    0.96
     blocks
    0.95
    Block
    0.91
     blok
    0.89
     Blok
    0.88
     ব্লক
    0.88
     blocked
    0.88
     ब्लॉक
    0.87
    Activations Density 0.015%

    No Known Activations