© 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. 67678
    Prev
    Next
    INDEX
    Explanations

    ectopic, Ecma, ecdysone, ecliptic

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

    The neuron is strongly activated by the sequence “Ec” (and its variants) – i.e. the “Ec” prefix in technical terms and abbreviations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     raiſ
    -3.42
    ︲
    -3.19
    ⚋
    -2.81
    鸸
    -2.81
    kinda
    -2.80
    鹩
    -2.75
     uſed
    -2.69
    ᛬
    -2.69
    ますが
    -2.63
    齁
    -2.63
    POSITIVE LOGITS
    {
    3.78
    ]
    3.52
    (
    3.44
    *
    3.31
    t
    3.16
    ↵↵
    2.77
    %
    2.73
    g
    2.64
    0
    2.64
    }
    2.63
    Activations Density 0.027%

    No Known Activations