© 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. 51506
    Prev
    Next
    INDEX
    Explanations

    names starting with Maria

    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
    lyl
    0.42
     Dharmendra
    0.42
    "/"
    0.42
    dinger
    0.40
    میم
    0.40
    ıma
    0.40
    🫤
    0.39
    ioane
    0.38
    alski
    0.38
    軐
    0.38
    POSITIVE LOGITS
     Magdalena
    0.41
     Antoinette
    0.41
     Luisa
    0.41
     diesel
    0.40
     Mercedes
    0.40
     magnesium
    0.40
    DB
    0.38
    jos
    0.37
     José
    0.37
     Edu
    0.37
    Activations Density 0.008%

    No Known Activations