© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67037
    Prev
    Next
    INDEX
    Explanations

    regardless of

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

    The neuron strongly activates on the word “content.”

    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
    ]));
    -2.13
    }}
    -2.05
     ´
    -1.98
     cornerstone
    -1.98
    }\
    -1.95
    тельства
    -1.83
    на
    -1.83
    }>
    -1.80
    私も
    -1.79
     gilded
    -1.76
    POSITIVE LOGITS
     that
    2.52
     who
    2.30
    it
    2.17
    which
    2.11
     it
    2.03
     there
    2.00
     preparada
    1.90
     eenig
    1.88
     understand
    1.85
     vestito
    1.85
    Activations Density 0.003%

    No Known Activations