© 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. 7385
    Prev
    Next
    INDEX
    Explanations

    branding

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

    This neuron activates strongly on the term “branding” (and its variants like “branded”) wherever it appears in 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
    al
    -2.67
    s
    -2.44
    on
    -2.39
    <bos>
    -2.36
    </h3>
    -2.33
    ].
    -2.27
    t
    -2.23
    ים
    -2.22
    or
    -2.13
    つけた
    -2.13
    POSITIVE LOGITS
    婓
    2.41
    ではまた
    2.34
    毉
    2.33
    !”,
    2.31
    　↓
    2.28
     kostenlosen
    2.23
    鸯
    2.20
    烀
    2.20
    ?!”
    2.19
    欒
    2.19
    Activations Density 0.002%

    No Known Activations