© 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. 12637
    Prev
    Next
    INDEX
    Explanations

    hypothetical clinical or responded clinical

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

    hypothetical or conditional statements often introduced by phrases like "could" or "might".

    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
     ویتامین
    -1.23
    ologische
    -1.17
     Estable
    -1.16
     deaktiviert
    -1.13
     milioane
    -1.12
    ipment
    -1.09
    Mesmo
    -1.09
    為什麼
    -1.08
    ichord
    -1.06
     概要
    -1.05
    POSITIVE LOGITS
     aplica
    1.13
        
    1.09
     yearly
    1.06
     work
    1.02
     our
    1.01
    se
    1.00
     works
    1.00
     sientes
    0.99
     set
    0.97
     #
    0.96
    Activations Density 0.146%

    No Known Activations