© 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. 34-GEMMASCOPE-RES-131K
    7. 91772
    Prev
    Next
    INDEX
    Explanations

    egg and its preparations

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

    food ingredients and recipe components in lists or descriptions.

    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
     plastik
    -0.94
     heng
    -0.94
     juni
    -0.93
     dayan
    -0.92
     ESPN
    -0.92
     paik
    -0.90
     vekt
    -0.90
     viera
    -0.90
     marmor
    -0.89
     ۱۲
    -0.89
    POSITIVE LOGITS
     melange
    0.91
     reckon
    0.91
     forfe
    0.85
     dictates
    0.84
    łania
    0.83
     любой
    0.82
     fastener
    0.82
    alarme
    0.81
     freaked
    0.81
     slaps
    0.81
    Activations Density 0.001%

    No Known Activations