© 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. 79426
    Prev
    Next
    INDEX
    Explanations

    random target generation

    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
     pozost
    0.46
     kimia
    0.44
     }}=
    0.44
     পর্যবে
    0.43
     கல்விய
    0.43
     }}=\
    0.43
    ombrie
    0.42
     Pupils
    0.42
     یې
    0.40
    籹
    0.40
    POSITIVE LOGITS
     lại
    0.45
    红包
    0.42
    0
    0.41
    Quite
    0.41
    يت
    0.40
    用来
    0.40
    墩
    0.39
    تي
    0.38
     pallet
    0.38
    ย
    0.38
    Activations Density 0.000%

    No Known Activations