© 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. 110048
    Prev
    Next
    INDEX
    Explanations

    breakthrough innovations

    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
    주
    0.47
    но
    0.46
     Governmental
    0.44
     Jerman
    0.44
    жных
    0.43
    новый
    0.43
     Soci
    0.43
    녁
    0.43
    荐
    0.43
    تمع
    0.42
    POSITIVE LOGITS
     بے
    0.48
     recite
    0.47
     mentally
    0.43
     condoms
    0.42
     whispered
    0.41
     whisper
    0.40
     braces
    0.40
     bake
    0.39
     depende
    0.39
    nahme
    0.38
    Activations Density 0.006%

    No Known Activations