© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15323
    Prev
    Next
    INDEX
    Explanations

    ike, iker, ikes, rike

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

    This neuron detects occurrences of the character sequence “ike” within words.

    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
    ).
    -4.47
    ?
    -3.05
    l
    -2.81
     \
    -2.73
    on
    -2.63
    ."
    -2.58
    ”.
    -2.56
    ....
    -2.50
     is
    -2.47
    `
    -2.41
    POSITIVE LOGITS
    geſ
    3.30
    ike
    2.72
    genodigd
    2.69
     sabun
    2.61
     dizendo
    2.59
     selam
    2.52
     gelas
    2.47
     Перейти
    2.41
     kemer
    2.38
     kabar
    2.36
    Activations Density 0.002%

    No Known Activations