© 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. 19958
    Prev
    Next
    INDEX
    Explanations

    localized power, Health Outcomes, Task blocks

    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
     شا
    0.53
    name
    0.48
    排列
    0.44
     সাফল
    0.43
    主动
    0.43
    indexing
    0.43
     శ
    0.42
    album
    0.42
    long
    0.42
    城
    0.42
    POSITIVE LOGITS
     Stahl
    0.53
     femelles
    0.52
     Beatriz
    0.52
     by
    0.51
     motores
    0.50
     бывают
    0.50
     boilers
    0.50
     calomel
    0.50
     grind
    0.50
     Lagrange
    0.50
    Activations Density 0.001%

    No Known Activations