© 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. 22741
    Prev
    Next
    INDEX
    Explanations

    lists of specific items

    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
     díky
    0.47
     খেয়ে
    0.46
    പ്പോഴും
    0.45
     grazie
    0.45
    恢复
    0.45
     ቫ
    0.44
    팽
    0.44
    简单
    0.44
    𝑬
    0.44
    quickly
    0.44
    POSITIVE LOGITS
     Länder
    0.48
     conquests
    0.44
     biographical
    0.42
     specifiche
    0.40
     समावेश
    0.39
    リューション
    0.39
     specifica
    0.39
     founders
    0.38
     indemn
    0.38
     rhetorical
    0.38
    Activations Density 0.006%

    No Known Activations