© 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. 31-GEMMASCOPE-2-RES-262K
    7. 78538
    Prev
    Next
    INDEX
    Explanations

    url link

    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_31_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
     незна
    0.54
    ьому
    0.54
    е
    0.50
    Это
    0.50
    叁章
    0.50
     उन्‍हें
    0.47
    େ
    0.47
    Ꭸ
    0.47
     детям
    0.46
    Khokhlov
    0.46
    POSITIVE LOGITS
     dealer
    0.48
     skate
    0.46
     lifeboat
    0.45
     back
    0.44
     fish
    0.44
     cruise
    0.44
     semble
    0.44
     bait
    0.43
     machine
    0.43
     sticker
    0.43
    Activations Density 0.012%

    No Known Activations