© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100075
    Prev
    Next
    INDEX
    Explanations

    PIC, Kid, verse, disjoint, asp, patients, region, lower, environment, history, Black

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

    terms related to specific environments, systems, or locations (like technical platforms, geographical areas, or physical contexts).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     on
    -2.31
     will
    -1.77
     what
    -1.73
     until
    -1.70
     ähn
    -1.54
     available
    -1.50
    on
    -1.48
     provides
    -1.45
     most
    -1.45
     all
    -1.43
    POSITIVE LOGITS
    姈
    1.57
     Depuis
    1.52
    鸸
    1.49
     transparan
    1.46
     bunda
    1.46
    婓
    1.43
    垟
    1.42
     作り方
    1.42
    今夜
    1.41
    我不知道
    1.38
    Activations Density 0.134%

    No Known Activations