© 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. 40-GEMMASCOPE-2-RES-65K
    7. 51888
    Prev
    Next
    INDEX
    Explanations

    Lindemann, Lindbergh, Lindon, Lindenhof

    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_40_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
    ethe
    0.37
    အတူ
    0.37
     Candid
    0.36
    檯
    0.36
     ер
    0.36
    ンダー
    0.35
     แจ
    0.35
    uyang
    0.34
    Brend
    0.34
     citing
    0.34
    POSITIVE LOGITS
    嫨
    0.44
    strom
    0.43
    相当
    0.38
     കൂടിയ
    0.38
    キュー
    0.38
    問い
    0.37
     வழியாக
    0.36
    糅
    0.36
     treacher
    0.35
     बिंदु
    0.35
    Activations Density 0.005%

    No Known Activations