© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65946
    Prev
    Next
    INDEX
    Explanations

    freeze-dried / lyophilization

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

    processes related to drying or dehydration techniques like freeze-drying, lyophilization, and sublimation.

    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
    躋
    -1.92
    ፨
    -1.73
    珦
    -1.73
    鶲
    -1.63
    朥
    -1.59
     ensu
    -1.53
    玧
    -1.52
    頃は
    -1.52
     väg
    -1.49
    粢
    -1.49
    POSITIVE LOGITS
    ’
    1.81
    e
    1.63
    -
    1.61
    \\
    1.52
    '
    1.44
    ဴ
    1.44
     '
    1.39
    以免
    1.38
    )
    1.34
    #
    1.30
    Activations Density 0.023%

    No Known Activations