© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 470
    Prev
    Next
    INDEX
    Explanations

    genetic codes and numbers

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

    numerical identifiers like reference numbers, database IDs, or catalog numbers.

    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
     emballage
    -1.20
     rév
    -1.20
    čiau
    -1.13
     guir
    -1.13
     még
    -1.12
     linge
    -1.11
     fantastisk
    -1.05
     moelle
    -1.05
     couver
    -1.04
     considérons
    -1.02
    POSITIVE LOGITS
    了自己
    1.19
    8
    1.18
    7
    1.13
     Lukaku
    1.10
    0
    1.09
    9
    1.08
     (!__
    1.08
     рассказа
    1.06
     القديمة
    1.05
    6
    1.04
    Activations Density 0.059%

    No Known Activations