© 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. 31-GEMMASCOPE-2-RES-262K
    7. 44254
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and abstract concepts

    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
     ισ
    0.50
     Zusätzlich
    0.48
    𒋀
    0.48
     дея
    0.46
     pią
    0.45
    ⟋
    0.44
    冋
    0.44
     μετα
    0.43
    ]，
    0.43
     同时
    0.43
    POSITIVE LOGITS
     solitaire
    0.49
     uncertainty
    0.48
     two
    0.47
     shopping
    0.47
    :
    0.47
    によって
    0.47
    two
    0.46
    altz
    0.46
    ucket
    0.46
     laisser
    0.46
    Activations Density 0.004%

    No Known Activations