© 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. 22-GEMMASCOPE-RES-131K
    7. 72129
    Prev
    Next
    INDEX
    Explanations

    news agencies and sources

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

    The neuron is looking for news‐source bylines or source attribution markers (e.g. “— Reuters,” “Source: PTI”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    eronau
    -1.07
     Ángeles
    -1.06
     tomates
    -1.02
     Kapol
    -1.01
    である
    -0.97
     Desenvolvimento
    -0.95
    parently
    -0.92
     mily
    -0.91
     вещь
    -0.91
     руках
    -0.91
    POSITIVE LOGITS
     with
    1.04
     füllen
    0.99
     sienta
    0.99
    </b>
    0.96
    </em>
    0.94
    lectual
    0.94
     THERE
    0.93
    ࣪
    0.93
     vetores
    0.93
    </strong>
    0.92
    Activations Density 0.003%

    No Known Activations