© 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. 22-GEMMASCOPE-RES-131K
    7. 39112
    Prev
    Next
    INDEX
    Explanations

    like this, similarity, operator

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

    The neuron detects occurrences of the word “like” (in any case).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ),
    -3.28
    ?
    -3.20
    ."
    -3.11
    ).
    -2.83
    t
    -2.78
     вслед
    -2.41
    !
    -2.34
     \
    -2.30
    ~
    -2.28
    ↵
    -2.20
    POSITIVE LOGITS
    𖣘
    2.77
    และ
    2.75
    ть
    2.66
    白的
    2.48
    ㇼ
    2.41
    »،
    2.36
    儅
    2.34
     turun
    2.33
    图源
    2.33
     mismos
    2.31
    Activations Density 0.096%

    No Known Activations