© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2376
    Prev
    Next
    INDEX
    Explanations

    Live cell, Flights from, Cor-tical, An-ata

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

    technical alphanumeric codes, especially when they appear in program code or system data.

    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
     trám
    -1.02
    athed
    -0.96
    beautiful
    -0.94
     pn
    -0.94
    cách
    -0.94
    gten
    -0.94
     remarkably
    -0.93
     ajout
    -0.92
     ajouter
    -0.92
     фильмы
    -0.91
    POSITIVE LOGITS
     for
    1.13
     in
    1.09
     with
    1.05
     or
    1.04
     maintains
    1.03
     šo
    1.02
     at
    0.97
     epitom
    0.94
     Since
    0.93
     Once
    0.92
    Activations Density 0.001%

    No Known Activations