© 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. 12649
    Prev
    Next
    INDEX
    Explanations

    switch to

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

    The neuron fires on words that signal upcoming actions or changes—especially future‐tense auxiliaries and directives like “will,” “now,” “switch,” etc.

    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
     llegaron
    -0.99
     formó
    -0.85
     estuvieron
    -0.85
    containsKey
    -0.82
     llegó
    -0.81
    addView
    -0.79
     Old
    -0.77
    แบ
    -0.77
     sostener
    -0.76
     oxígeno
    -0.75
    POSITIVE LOGITS
     now
    1.35
     excepcional
    1.07
    これを
    1.06
     restantes
    0.96
     will
    0.95
    liction
    0.93
     ahora
    0.92
     PARTIES
    0.90
    使其
    0.90
     fasse
    0.89
    Activations Density 0.044%

    No Known Activations