© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30931
    Prev
    Next
    INDEX
    Explanations

    anabolic, anaerobic, anaphylactic

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

    medical or scientific terminology prefixes like "ana-" in words such as "anabolic", "anaerobic", and "anaphylaxis".

    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_34/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
    に関
    -0.78
    tibus
    -0.78
     cuál
    -0.78
     allgemeinen
    -0.77
     rattles
    -0.75
    你可
    -0.74
     offen
    -0.73
    ͫ
    -0.73
    Otro
    -0.73
     Everyday
    -0.73
    POSITIVE LOGITS
     ana
    1.13
    Ana
    1.13
     Ana
    1.09
    ана
    0.85
    plan
    0.85
     вдруг
    0.84
     Ана
    0.83
     ана
    0.81
     ανα
    0.81
     godine
    0.81
    Activations Density 0.026%

    No Known Activations