© 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. 84456
    Prev
    Next
    INDEX
    Explanations

    Russian adjective suffixes followed by nouns

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

    The neuron activates on Russian adjectives.

    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
     we
    -2.77
    </sub>
    -2.66
    馓
    -2.63
    e
    -2.58
    圌
    -2.47
    a
    -2.41
    помним
    -2.36
    “
    -2.33
    </strong>
    -2.31
    queous
    -2.25
    POSITIVE LOGITS
    \
    2.77
    呦
    2.64
    ﾜ
    2.55
    the
    2.47
    ～～～
    2.36
    This
    2.33
     Gedanke
    2.30
    ｱ
    2.30
    喲
    2.25
     Contrary
    2.16
    Activations Density 0.007%

    No Known Activations