© 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. 58689
    Prev
    Next
    INDEX
    Explanations

    promo video, codes, price, flyers

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

    The neuron activates on any token containing the substring “promo” (e.g. promo, promos, promotional).

    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
    }
    -2.94
     are
    -2.56
     Their
    -2.44
     dlatego
    -2.44
    ]
    -2.25
    ми
    -2.22
     która
    -2.20
     newest
    -2.19
     Mitgliedern
    -2.19
     problémy
    -2.14
    POSITIVE LOGITS
     faſt
    2.30
    榈
    2.27
    ことができ
    2.11
    龇
    2.11
    ꦏ
    2.08
     resten
    2.08
    胧
    2.06
    ”，
    2.03
     ἄ
    2.02
    可以说是
    2.02
    Activations Density 0.001%

    No Known Activations