© 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. 10-GEMMASCOPE-RES-131K
    4. 621
    Prev
    Next
    INDEX
    Explanations

    drug addiction or mental illness

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

    the word "offender" or "offenders" in criminal justice and legal contexts.

    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_10/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
     flyg
    -2.66
     étaient
    -2.59
     intertw
    -2.52
     emballage
    -2.47
     abiye
    -2.33
     compagnon
    -2.31
    粜
    -2.27
    ні
    -2.25
     suure
    -2.22
    y
    -2.22
    POSITIVE LOGITS
     to
    2.58
    骓
    2.30
    ~。
    2.13
     ältere
    2.08
    ~!
    2.08
     And
    2.08
     and
    2.08
    穫
    2.06
    柃
    2.02
     ступен
    1.98
    Activations Density 0.005%

    No Known Activations