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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12372
    Prev
    Next
    INDEX
    Explanations

    HIV control, Q:

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

    Numbers in the text, especially numeric identifiers.

    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
    ;
    -1.22
     to
    -1.22
     cuyo
    -1.17
     erzeugen
    -1.13
     t
    -1.12
     from
    -1.10
     p
    -1.05
     конструкции
    -1.05
     *
    -1.04
     j
    -1.04
    POSITIVE LOGITS
    スポンサーリンク
    1.35
    ׃
    1.33
    
    1.30
     saisi
    1.29
     gitu
    1.28
    >
    
    
    1.28
    PUESTA
    1.28
     australis
    1.27
     ботинки
    1.26
     disponibilités
    1.24
    Activations Density 0.000%

    No Known Activations