© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127212
    Prev
    Next
    INDEX
    Explanations

    player attributes and identifiers

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

    The neuron strongly activates on the token “player,” i.e. occurrences of the word “player” in code or text.

    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
    y
    -2.78
    </strong>
    -2.59
    ↵
    -2.47
    u
    -2.42
    on
    -2.34
     they
    -2.34
    and
    -2.28
    </em>
    -2.22
    </h4>
    -2.22
    ,"
    -2.19
    POSITIVE LOGITS
    
    2.69
    इटम
    2.63
    नलोड
    2.47
    ølge
    2.34
    MAXN
    2.17
    ﾅ
    2.13
    Ꮉ
    2.13
    ează
    2.13
    Ꮂ
    2.11
    ちゃんは
    2.09
    Activations Density 0.005%

    No Known Activations