© 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. 59612
    Prev
    Next
    INDEX
    Explanations

    behind the scenes information

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

    The neuron detects mentions of “behind the scenes” or related backstage-style 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
     any
    -1.85
     ANY
    -1.60
     cualquier
    -1.48
     your
    -1.46
     buscan
    -1.42
     extremadamente
    -1.42
     大阪
    -1.41
     neuen
    -1.40
     aktuellen
    -1.38
    говори
    -1.36
    POSITIVE LOGITS
     of
    1.88
    </strong>
    1.59
     insider
    1.50
    s
    1.48
     noten
    1.43
     between
    1.36
    ᯅ
    1.35
     behind
    1.32
    并未
    1.32
     comedor
    1.31
    Activations Density 0.023%

    No Known Activations