© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75496
    Prev
    Next
    INDEX
    Explanations

    racing

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

    The neuron specifically detects the word “racing” (and close variants of that term).

    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
    ()]);
    -2.64
    肏
    -2.48
    </h2>
    -2.28
    ]]);
    -2.14
    </h4>
    -2.13
    }
    
    -2.03
    紧接着
    -2.02
    씻
    -1.99
    入った
    -1.98
    最后由
    -1.95
    POSITIVE LOGITS
    )
    2.63
    那里
    2.23
    of
    2.13
     myriad
    2.11
    </i>
    2.05
    x
    2.05
    -
    2.00
     waren
    1.98
     dismay
    1.96
     beweg
    1.95
    Activations Density 0.008%

    No Known Activations