© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9105
    Prev
    Next
    INDEX
    Explanations

    naming someone or something

    np_acts-logits-general · gemini-2.5-flash-lite

    namesake, named, or naming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilized
    0.39
    uos
    0.36
    ubhav
    0.36
    รม
    0.35
    garbage
    0.35
     વૈ
    0.34
    isição
    0.34
    <unused0>
    0.34
     Nol
    0.33
     விசாரணை
    0.33
    POSITIVE LOGITS
     named
    2.92
    named
    2.70
     Named
    2.70
     namesake
    2.63
    Named
    2.53
     naming
    2.52
     নামকরণ
    2.52
     name
    2.45
    命名
    2.44
     이름을
    2.44
    Activations Density 0.527%

    No Known Activations