© 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-65K
    7. 45784
    Prev
    Next
    INDEX
    Explanations

    mathematical expression and calculation

    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_65k_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
     ná
    0.48
     itch
    0.41
    świet
    0.39
    Ná
    0.39
    ">→</
    0.38
     Öl
    0.38
     ніж
    0.38
     હોય
    0.38
     Örneğin
    0.38
    喎
    0.38
    POSITIVE LOGITS
     obeys
    0.44
     abh
    0.40
    f
    0.39
    tf
    0.39
    mph
    0.39
     notor
    0.39
     exp
    0.38
    with
    0.38
     والن
    0.38
     with
    0.37
    Activations Density 0.008%

    No Known Activations