© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112054
    Prev
    Next
    INDEX
    Explanations

    cryptic or crypto related words

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

    The neuron is triggered by subwords related to “crypt” (e.g. crypt-analytic, cryptographic, Cryptosporidium, cryptic, etc.).

    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
    '
    -1.98
     said
    -1.96
    泐
    -1.95
    他能
    -1.92
    (
    -1.84
    ?'
    -1.81
    You
    -1.78
    阿姨
    -1.77
    襌
    -1.77
    )(
    -1.73
    POSITIVE LOGITS
    他的
    2.16
    缟
    2.16
     花纹
    2.11
    扪
    1.92
     剧照
    1.90
     کرت
    1.89
     炖
    1.87
    Neymar
    1.85
    bringung
    1.85
     círculos
    1.84
    Activations Density 0.015%

    No Known Activations