© 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. 22-GEMMASCOPE-RES-131K
    7. 66580
    Prev
    Next
    INDEX
    Explanations

    politics, science, and species

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

    information about rules, guidelines, or technical specifications.

    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_22/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
     also
    -1.19
     predominant
    -1.15
     this
    -0.93
     for
    -0.93
     strong
    -0.92
     five
    -0.90
     principal
    -0.90
     modest
    -0.90
     self
    -0.88
     power
    -0.88
    POSITIVE LOGITS
     både
    1.21
     presentó
    1.12
     celebró
    1.03
    눙
    1.02
    demort
    1.02
    Literally
    1.01
     behandel
    0.99
     envíos
    0.98
     píše
    0.98
    órica
    0.97
    Activations Density 0.091%

    No Known Activations