© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71103
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron fires on occurrences of the character sequence “Rosen” (i.e. names or terms containing “Rosen”).

    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
    ться
    -3.06
    ⵌ
    -2.72
    9
    -2.72
    有很多
    -2.67
    たまに
    -2.56
    しっかり
    -2.53
     acclaimed
    -2.50
    usually
    -2.50
     momentous
    -2.50
    ホント
    -2.45
    POSITIVE LOGITS
    酲
    3.02
    </em>
    2.69
    𝐲
    2.66
    <em>
    2.63
    旅館
    2.41
     That
    2.36
    最后由
    2.33
    <bos>
    2.33
    并将
    2.30
    籐
    2.28
    Activations Density 0.007%

    No Known Activations