© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12227
    Prev
    Next
    INDEX
    Explanations

    health and safety advice

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

    bullet points or list items in instructional/tips content.

    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
    ⇑
    -1.07
     necesaria
    -1.06
    lase
    -1.05
    fähig
    -1.04
    Aho
    -1.01
    𝚡
    -1.01
     here
    -1.00
    vábbi
    -0.99
     ModelExpression
    -0.99
     braço
    -0.96
    POSITIVE LOGITS
     use
    1.48
     avoid
    1.24
    Avoid
    1.16
     esimerkiksi
    1.15
     switch
    1.10
    zések
    1.09
     lorsqu
    1.08
     استفاده
    1.08
    itaji
    1.08
     wisely
    1.05
    Activations Density 0.030%

    No Known Activations