© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112136
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

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

    the word "Maison" (particularly in the context of the French design house Maison Baguès).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unſ
    -2.55
    橛
    -2.53
    RequiresApi
    -2.47
     asses
    -2.45
     nerede
    -2.44
    yym
    -2.41
     gobier
    -2.38
    遹
    -2.30
    蜩
    -2.23
    釭
    -2.22
    POSITIVE LOGITS
     Hinsicht
    2.61
    A
    2.52
    It
    2.42
    i
    2.23
    最为
    2.23
    «
    2.19
     maison
    2.16
    >
    2.13
    伝統
    2.11
    あえず
    2.09
    Activations Density 0.000%

    No Known Activations