© 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. 73805
    Prev
    Next
    INDEX
    Explanations

    Cairo, King Cairo, cariogenic, Kairuku, airbag

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

    This neuron fires on occurrences of the place name “Cairo.”

    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
    O
    -2.59
    y
    -2.48
    al
    -2.44
     erneu
    -2.34
    d
    -2.31
    甚至是
    -2.31
    '
    -2.30
    🡺
    -2.30
    “
    -2.28
     sorgt
    -2.23
    POSITIVE LOGITS
    猡
    2.41
    ные
    2.39
    ி
    2.31
     Zerst
    2.08
    of
    2.06
     Küste
    2.05
    螄
    2.05
    ктором
    2.03
     the
    2.02
     दौरान
    2.02
    Activations Density 0.001%

    No Known Activations