© 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. 101888
    Prev
    Next
    INDEX
    Explanations

    fantastical, dimethyl, hematopoietica, emphasizes, fantasies

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

    chemical and scientific terminology, particularly words containing "methyl," "forma," and technical compound names.

    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
    ség
    -3.19
     dovr
    -3.05
    玠
    -2.88
    Skocz
    -2.86
    ﮯ
    -2.81
    轳
    -2.72
     Strukt
    -2.72
     responsabile
    -2.67
    髕
    -2.67
     accedi
    -2.66
    POSITIVE LOGITS
    a
    3.72
    -
    3.28
     –
    2.97
    To
    2.91
     “
    2.81
    ar
    2.78
     (
    2.72
    ”
    2.56
    er
    2.56
     «
    2.53
    Activations Density 0.005%

    No Known Activations