© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22483
    Prev
    Next
    INDEX
    Explanations

    Kiwi Aussie khaki

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

    The neuron responds to tokens containing the “k” sound (i.e. the letter K), highlighting words like Kiwi, khaki, husky, DJ Quik, Mango, brumm, 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
    ↵
    -4.31
    }
    -3.63
     wichtigste
    -2.72
     vollständige
    -2.63
    ”
    -2.53
     erweiter
    -2.50
     erforder
    -2.47
    ]
    -2.41
    '
    -2.41
    翃
    -2.33
    POSITIVE LOGITS
     apparaissent
    2.47
    })}
    2.42
     exercices
    2.34
    捽
    2.33
    joyed
    2.31
    itizing
    2.25
     ставить
    2.23
     inappropriés
    2.22
    Ꮄ
    2.20
    2.17
    Activations Density 0.005%

    No Known Activations