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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58445
    Prev
    Next
    INDEX
    Explanations

    intramuscular injections and treatments

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

    Java/programming annotations like @dataclass, @NoArgsConstructor, and medical terms related to intramuscular treatments.

    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
    鋦
    -2.59
    y
    -2.44
    इटम
    -2.38
    ’，
    -2.33
    {
    -2.19
    ейчас
    -2.16
    鬭
    -2.14
    锱
    -2.13
    ㍑
    -2.03
    ໊
    -2.00
    POSITIVE LOGITS
    ArgsConstructor
    2.84
    没什么
    2.41
    U
    2.23
    <td>
    2.19
    T
    2.09
    不是很
    2.06
    的确
    2.05
     —
    2.05
    ]--;
    2.05
    Q
    2.03
    Activations Density 0.001%

    No Known Activations