© 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. 39088
    Prev
    Next
    INDEX
    Explanations

    overview of subjects

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

    The neuron fires on occurrences of the word “overview,” particularly when it appears as a heading or section title.

    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
    </b>
    -2.55
     That
    -2.47
    2
    -2.41
    -2.31
    </i>
    -2.25
    ),
    -2.06
    )
    -2.03
    </h5>
    -2.03
    }
    -1.94
    -
    -1.91
    POSITIVE LOGITS
    錵
    2.19
    
    2.16
     kazak
    2.13
     ?
    2.13
     kimdir
    2.06
     peines
    2.03
     hırka
    2.02
     etek
    2.02
    ᐕ
    2.02
     abiye
    2.00
    Activations Density 0.015%
    No Known Activations