© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28417
    Prev
    Next
    INDEX
    Explanations

    press release or conference

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

    The neuron activates on mentions of “press release,” effectively detecting when a press release is referenced.

    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
     to
    -1.55
    他の
    -1.38
    基本的に
    -1.33
    もしか
    -1.33
    などの
    -1.33
    がなく
    -1.26
     perda
    -1.25
    は
    -1.23
     also
    -1.23
    also
    -1.22
    POSITIVE LOGITS
     this
    1.63
     costuras
    1.33
     eenig
    1.27
     pegatinas
    1.20
     embrague
    1.17
    ﺮ
    1.17
     şir
    1.15
     ツリー
    1.15
     titolata
    1.13
    🪙
    1.13
    Activations Density 0.039%

    No Known Activations