© 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. 34-GEMMASCOPE-RES-131K
    7. 106569
    Prev
    Next
    INDEX
    Explanations

    organic chains such as

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

    academic citation patterns with brackets and reference identifiers following the [@pone] format.

    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
     incrí
    -1.10
     camiset
    -1.10
     europé
    -1.05
     saati
    -1.05
     ۹
    -1.04
     parachoque
    -1.04
     PLAYING
    -1.03
     ۱۸
    -1.02
     💜
    -1.02
     séjours
    -1.02
    POSITIVE LOGITS
     van
    1.45
     others
    1.33
     other
    1.30
     Lee
    1.15
     Van
    1.04
    𐄙
    1.01
     authors
    1.01
     Jennifer
    1.00
     innym
    0.98
     Others
    0.98
    Activations Density 0.597%

    No Known Activations