© 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. 60734
    Prev
    Next
    INDEX
    Explanations

    berberine, bernstein, berlin, berne

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

    The neuron fires on any occurrence of the character sequence “ber” (in any context), highlighting that trigram wherever it appears in a token.

    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
    j
    -2.88
    al
    -2.72
    g
    -2.59
    '
    -2.53
    us
    -2.41
    ↵↵
    -2.39
    li
    -2.23
    i
    -2.22
     leur
    -2.20
    in
    -2.14
    POSITIVE LOGITS
    푉
    2.44
     excruciating
    2.44
    鲻
    2.42
    बाइल
    2.41
     Einige
    2.36
     AFTER
    2.36
     Bemerkungen
    2.36
    艫
    2.36
    orsese
    2.34
    罴
    2.34
    Activations Density 0.013%

    No Known Activations